AAAI 2026 Accepted Papers

The full list of 4,902 papers accepted at AAAI 2026 (Association for the Advancement of Artificial Intelligence Annual Conference on Artificial Intelligence). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Technical: 4,902

Native Speech Processing with LLMsTechnical
Navigating Through Paper Flood: Advancing LLM-Based Paper Evaluation Through Domain-Aware Retrieval and Latent ReasoningTechnical
Navigating the Alpha Jungle: An LLM-Powered MCTS Framework for Formulaic Alpha Factor MiningTechnical
Navigation and Interaction for Blind Users via a Cognitive ArchitectureTechnical
NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language ModelsTechnical
Near-optimal Linear Predictive Clustering in Non-separable Spaces via MIP and QPBO ReductionsTechnical
Negative Entity Suppression for Zero-Shot Captioning with Synthetic ImagesTechnical
Neighbor-aware Instance Refining with Noisy Labels for Cross-Modal RetrievalTechnical
Neighbor-aware Label Refinement: Enhancing Unreliable Instance-Dependent Partial LabelsTechnical
Nested Depth SearchTechnical
Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation LearningTechnical
Network Inversion for Uncertainty-Aware Out-of-Distribution Detection (Student Abstract)Technical
Network Restoration Games with Quotas (Student Abstract)Technical
NeuPAN: Direct Point Robot Navigation with End-to-End Model-Based Learning (Abstract Reprint)Technical
NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic ReasoningTechnical
NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from VideosTechnical
Neural Architecture and Hyperparameter Selection Through Meta-Learning on Time SeriesTechnical
Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging ThromboelastographyTechnical
Neural Collapse Priors Driven Trust Semi-Supervised Multi-View ClassificationTechnical
Neural Collapse-Informed Initialization with Perturbation Injection in Classification-based Metric LearningTechnical
Neural Graph Navigation for Intelligent Subgraph MatchingTechnical
Neural Outline Cache for Real-time Anti-aliasing Font RenderingTechnical
Neural Tangent Kernels Under Stochastic Data AugmentationTechnical
Neural Video Compression with Reference HierarchyTechnical
Neural-Augmented Kelvinlet for Real-Time Soft Tissue Deformation ModelingTechnical
NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D RepresentationsTechnical
NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal SimulationTechnical
Neuro-Symbolic Federated Learning over Heterogeneous Data-Views: A Structured Approach to Distributive EHR ModellingTechnical
NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic AlignmentTechnical
New Metrics for Disambiguating Feature Overlap and Catastrophic Forgetting in Incremental Learning Contexts (Student Abstract)Technical
New Synthetic Goldmine: Hand Joint Angle-Driven EMG Data Generation Framework for Micro-Gesture RecognitionTechnical
NewsLensAI: NER-Guided Summarization for Mitigating Hallucination and Bias in LLM-Based News Summaries (Student Abstract)Technical
Next Generation Active Learning: Mixture of LLMs in the LoopTechnical
Next Generation of Empirical Performance PredictionTechnical
Next Patch Prediction for AutoRegressive Visual GenerationTechnical
Next-Generation Metalens Vision System: Powered by AI and Applied to AITechnical
Nighttime Flare Removal via Wavelet-Guided and Gated-Enhanced Spatial-Frequency Fusion NetworkTechnical
No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained EmbeddingTechnical
NoMoColor: Unified Noise Modulation for Enhanced Diffusion-based Image Colorization (Student Abstract)Technical
NoReGeo: Non-Reasoning Geometry BenchmarkTechnical
Noise-Aware Graph-Based Cognitive Diagnostic Framework Through Low-Rank AlignmentTechnical
Noisy Correspondence Learning with Modality Gap Direction CorrectionTechnical
Non-Monotonic S4F Standpoint LogicTechnical
Non-Monotonicity in Fair Division of GraphsTechnical
Not All Distortions Are Created Equal: Distortion-Selective Domain Adaptation for Point Cloud Quality AssessmentTechnical
Not All Inconsistency Is Equal: Decomposing LVLM Uncertainty into Belief Divergence and Belief ConflictTechnical
Not All Tokens Are Meant to Be ForgottenTechnical
Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination MitigationTechnical
Not Everything Is Permitted: Constrained Cartesian Abstractions for Optimal Classical PlanningTechnical
Not Just What’s There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-TuningTechnical
Not Just for Archiving: Provable Benefits of Reusing the Archive in Evolutionary Multi-objective OptimizationTechnical
Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical NotesTechnical
NucEL: Single-Nucleotide ELECTRA-Style Genomic Pre-training for Efficient and Interpretable RepresentationsTechnical
NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive LearningTechnical
NutriScreener: Retrieval Augmented Multi-Pose Graph Attention Network for Malnourishment ScreeningTechnical
O-DisCo-Edit: Object Distortion Control for Unified Realistic Video EditingTechnical
O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language ModelTechnical
OAD-Promoter: Enhancing Zero-Shot VQA Using Large Language Models with Object Attribute DescriptionTechnical
ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon TasksTechnical
OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image SegmentationTechnical
OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Documents ArchiveTechnical
OMEGA: An Ontology-Driven Tool for Explaining Multi-Agent Path FindingTechnical
OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop RetrievalTechnical
OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting During Parameter-Efficient Fine-TuningTechnical
OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding AttacksTechnical
OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement LearningTechnical
ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data ElicitationTechnical
ORTCL: Towards Continual Learning of Time Series Foundation Models on Streaming Data via Orthogonal RotationTechnical
ORVIT: Near-Optimal Online Distributionally Robust Reinforcement LearningTechnical
OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System VerificationTechnical
OT-ALD: Aligning Latent Distributions with Optimal Transport for Accelerated Image-to-Image TranslationTechnical
OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMsTechnical
OTI: A Model-free and Visually Interpretable Measure of Image AttackabilityTechnical
OW-DAR: Dual-Granularity Adaptive Reconstruction-Error Modeling for Open-World Object DetectionTechnical
OWL: Unsupervised 3D Object Detection by Occupancy Guided Warm-up and Large Model Priors ReasoningTechnical
OX-MABSR: A Benchmark for Open-domain Explainable Multimodal Aspect-Based Sentiment ReasoningTechnical
Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options (Student Abstract)Technical
ObjecTok: Learning Holistic and Robust Object Tokens for MLLMsTechnical
Object Fusion via Diffusion Time-step for Customized Image Editing with Single ExampleTechnical
Object-Centric Data Synthesis for Category-level Object Detection (Student Abstract)Technical
Object-Centric Framework for Video Moment RetrievalTechnical
Object-Centric Latent Action LearningTechnical
Object-Centric World Models for Causality-Aware Reinforcement LearningTechnical
ObjectAdv: Object-Level Unrestricted Adversarial Attacks via Diffusion ModelsTechnical
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language ModelsTechnical
OccamVTS: Distilling Vision Models to 1% Parameters for Time Series ForecastingTechnical
OceanSplat: Object-aware Gaussian Splatting with Trinocular View Consistency for Underwater Scene ReconstructionTechnical
Octopus: Entropy-Controlled Science Fiction Literature Generation with Persistent Memory-Context BindingTechnical
Offline Fictitious Self-Play for Competitive GamesTechnical
Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature OvergeneralizationTechnical
Offline Multi-Objective Bandits: From Logged Data to Pareto-Optimal PoliciesTechnical
Oligodendrocyte-Driven Spiking Neural ModelTechnical
Omni-Effects: Unified and Spatially-Controllable Visual Effects GenerationTechnical
OmniBench: A Comprehensive Benchmark Integrating Real-World, Time-sensitive, and Multi-Hop Questions with a Multi-Dimensional Hybrid Evaluation FrameworkTechnical
OmniDPO: A Preference Optimization Framework to Address Omni-Modal HallucinationTechnical
OmniEvent: Unified Event Representation LearningTechnical
OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and UnderstandingTechnical
OmniScale: Scaling Any Modality Model Training with Model-Centric Distributed Recipe ZooTechnical
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMsTechnical
OmniVDiff: Omni Controllable Video Diffusion for Generation and UnderstandingTechnical
On Condorcet’s Jury Theorem with AbstentionTechnical
On Coresets for End-to-end Learning from CrowdsTechnical
On Generating Monolithic and Model Reconciling Explanations in Probabilistic Scenarios (Abstract Reprint)Technical
On Logical Extrapolation for Mazes with Recurrent and Implicit NetworksTechnical
On Modality Weighting and Specificity for Multi-Modal Entity AlignmentTechnical
On Model and Data Scaling for Skeleton-based Self-Supervised Gait RecognitionTechnical
On Robustness of Linear Classifiers to Targeted Data PoisoningTechnical
On Stealing Graph Neural Network ModelsTechnical
On Trustworthy, Explainable, and Verifiable High-Level Autonomy via Hierarchical PlanningTechnical
On the Approximation Ratio of Optimal Fixed-Price Mechanisms for Single and Multi-Unit Bilateral TradeTechnical
On the Calibration of Image Semi-Supervised Learning ModelsTechnical
On the Computational Tractability of Probabilistic Global and Local Sufficient ExplanationTechnical
On the Dataless Training of Neural NetworksTechnical
On the Edge of Core (Non-)Emptiness: An Automated Reasoning Approach to Approval-Based Multi-Winner VotingTechnical
On the Evaluation of Capability Estimation Methods for Large Language ModelsTechnical
On the Exponential Convergence for Offline RLHF with Pairwise ComparisonsTechnical
On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering AttacksTechnical
On the Impact of Weight Quantization on Deep Neural Network UncertaintyTechnical
On the Information Processing of One-Dimensional Wasserstein Distances with Finite SamplesTechnical
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGDTechnical
On the Misalignment Between Data Learnability and Forgettability in Machine UnlearningTechnical
On the Probabilistic Learnability of Compact Neural Network Preimage BoundsTechnical
On the Robustness of Bandit Multiple TestingTechnical
On the Superimposed Noise Accumulation Problem in Sequential Knowledge Editing of Large Language ModelsTechnical
OnEDIT: Online Editing with Decoupled Implicit Task for Large Language ModelsTechnical
OncoCoT: A Temporal-causal Chain-of-Thought Dataset for Oncologic Decision-MakingTechnical
One for All: Synthesis-Free Fingerprint Learning for Attribution of In-the-Wild Synthetic ImagesTechnical
One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step DiffusionTechnical
One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlowTechnical
One2Seq: One-Token Wise Decoder for Efficient Scene Text RecognitionTechnical
OneFont: A Unified Agent for End-to-End Font CreationTechnical
OneLIP: Unlocking and Improving Long-Text Representations of CLIP via One-Stage AdaptationTechnical
OneSug: The Unified End-to-End Generative Framework for E-commerce Query SuggestionTechnical
Online Capacitated General Matching with KnapsackTechnical
Online Conformal Selection with Accept-to-Reject ChangesTechnical
Online Cross-Modal Hashing with Expanding Label SpaceTechnical
Online Fair Allocations with Binary Valuations and BeyondTechnical
Online Linear Regression with Paid Stochastic FeaturesTechnical
Online Multi-LLM Selection via Contextual Bandits Under Unstructured Context EvolutionTechnical
Online Multi-Relational Clustering with Dominant View MiningTechnical
Online Robust Planning Under Model Uncertainty: A Sample-Based ApproachTechnical
OnlineBootKNN: An Unsupervised Framework for Detecting Anomalies in Spectral Data StreamsTechnical
Open-World 3D Scene Graph Generation for Retrieval-Augmented ReasoningTechnical
Open-World Deepfake Attribution via Confidence-Aware Asymmetric LearningTechnical
Open-World Object Counting in VideosTechnical
OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action ModelTechnical
OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene UnderstandingTechnical
Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model BehaviorTechnical
Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware ExploitationTechnical
OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time OptimizationTechnical
OptScale: Probabilistic Optimality for Inference-time ScalingTechnical
OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical ModelingTechnical
Optimal Look-back Horizon for Time Series Forecasting in Federated LearningTechnical
Optimal Welfare in Noncooperative Network Formation Under AttackTechnical
Optimally Auditing Adversarial AgentsTechnical
Optimisation Problems in Constrained Machine LearningTechnical
Optimization Method for Surrogate Function in Spiking Neural Networks Based on Membrane Potential DistributionTechnical
Optimization and Robustness-Informed Membership Inference Attacks for LLMsTechnical
Optimization of Multi-Agent Flying Sidekick Traveling Salesman Problem over Road NetworksTechnical
Optimized Algorithms for Text Clustering with LLM-Generated ConstraintsTechnical
Optimized Distortion in Linear Social ChoiceTechnical
Optimizing Health Coverage in Ethiopia: A Learning-augmented Approach and Persistent Proportionality Under an Online BudgetTechnical
Optimizing LoRA Allocation of MoE with the Alignment of Topic CorrelationTechnical
Optimizing Preferential Rate in Retail Lending with Causal Inference and Domain AdaptationTechnical
Optimizing Product Provenance Verification Using Data Valuation MethodsTechnical
Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off FlexibilityTechnical
Optimizing Urban Service Allocation with Time-Constrained Restless BanditsTechnical
OrcheCause Agent: From Textual Knowledge to End-to-End Causal InferenceTechnical
Order-Preserving Dimension Reduction for Multimodal Semantic EmbeddingTechnical
Ordered Local Momentum for Asynchronous Distributed Learning Under Arbitrary DelaysTechnical
Ordered Objectives in Maximum SatisfiabilityTechnical
Ordinal Secretaries with AdviceTechnical
OrgaCast: A Trustworthy Spatiotemporal Diffusion Model for Fluorescence Organoid ForecastingTechnical
Organ-Aware Routing Mixture-of-Retrieval Augmented Generation for Fetal Ultrasound ReportingTechnical
Orion: Steering Personalized Web Agents via Global-Micro Profiling and Adaptive Intent TrackingTechnical
Orthogonal Spatial-temporal Distributional Transfer for 4D GenerationTechnical
Oscillation Inversion: Training-Free Image and Video Enhancement Through Oscillated Latents in Large Flow ModelsTechnical
OscuFit: Learning to Fit Osculating Implicit Quadrics for Point CloudsTechnical
Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent SpaceTechnical
Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKVTechnical
OursFed: Provable Group Fairness-Aware Federated Learning Against Distrust and FragilityTechnical
Out-of-Context Misinformation Detection via Variational Domain-Invariant Learning with Test-Time TrainingTechnical
Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language ModelsTechnical
Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single PolicyTechnical
Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model MergingTechnical
OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence RewardTechnical
Oxytrees: Model Trees for Bipartite LearningTechnical
P-SLCR: Unsupervised Point Cloud Semantic Segmentation via Prototypes Structure Learning and Consistent ReasoningTechnical
P2S: Probabilistic Process Supervision for General-Domain Reasoning Question AnsweringTechnical
PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement LearningTechnical
PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc TeamworkTechnical
PAGE: A Unified Approach for Federated Graph UnlearningTechnical
PAGER: Proactive Monitoring Agent for Enterprise AI AssistantTechnical
PAGPL: Privacy-Aware Graph Prompt Learning Scheme via Adaptive Perturbation-Estimated Topology RecoveryTechnical
PAL: Personal Adaptive LearnerTechnical
PANDA – Patch and Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual LearningTechnical
PANDA: Empowering Small Language Models for Proactive Dialogue Through Agent-Based Synthesis (Student Abstract)Technical
PANSim: Visualization Tool for Planning and Acting against NatureTechnical
PARS: Partial-Label-Learning-inspired Recommender SystemsTechnical
PASA: Progressive-Adaptive Spectral Augmentation for Automated Auscultation in Data-Scarce EnvironmentsTechnical
PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech EnhancementTechnical
PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray ReasoningTechnical
PATexGS: Perceptual-Adaptive Texture Scheduling for Visual Coherence in Textured Gaussian SplattingTechnical
PBR3DGen: A VLM-Guided Mesh Generation with High-Quality PBR TextureTechnical
PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and SegmentationTechnical
PC-Flow: Preference Alignment in Flow Matching via ClassifierTechnical
PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and CombinationTechnical
PCGS: Progressive Compression of 3D Gaussian SplattingTechnical
PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence LearningTechnical
PCoKG: Personality-aware Commonsense Reasoning with DebateTechnical
PDE-Driven Spatiotemporal Generative Modeling for Multilead ECG SynthesisTechnical
PEFT-BoA: Parameter-Efficient Fine-Tuning with Bag-of-Adapters for Multi-Modal Object Re-identificationTechnical
PEFT-DML: Parameter-Efficient Fine-Tuning Deep Metric Learning for Robust Multi-Modal 3D Object Detection in Autonomous Driving (Student Abstract)Technical
PEGNet: A Physics-Embedded Graph Network for Long-Term Stable Multiphysics SimulationTechnical
PEOAT: Personalization-Guided Evolutionary Question Assembly for One-Shot Adaptive TestingTechnical
PEOCH: Online Cross-Modal Hashing with Semi-Supervised Streaming Data Driving Prototype EvolutionTechnical
PEOD: A Pixel-Aligned Event-RGB Benchmark for Object Detection Under Challenging ConditionsTechnical
PET2Rep: Towards Vision-Language Model-Drived Automated Radiology Report Generation for Positron Emission TomographyTechnical
PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day PhotosTechnical
PGMamba: A Physical Model-Guided Global Mamba for Underwater Image EnhancementTechnical
PHOTONS: Pose-Free Human-Centric Photo-Realistic Real-Time Novel View Synthesis from Sparse ViewsTechnical
PHPFND: Detecting Fake News via Post-Hoc Processing of LLMs HallucinationTechnical
PIF-Net: Ill-Posed Prior Guided Multispectral and Hyperspectral Image Fusion via Invertible Mamba and Fusion-Aware LoRATechnical
PIMRL: Physics-Informed Multi-Scale Recurrent Learning for Burst-Sampled Spatiotemporal DynamicsTechnical
PINGS-X: Physics-Informed Normalized Gaussian Splatting with Axes Alignment for Efficient Super-Resolution of 4D Flow MRITechnical
PINet: Improving the Stability of Prototype Networks via Phantasia-Inspired Uncertain RepresentationsTechnical
PIPHEN: Physical Interaction Prediction with Hamiltonian Energy NetworksTechnical
PITE: Multi-Prototype Alignment for Individual Treatment Effect EstimationTechnical
PKR-QA: A Benchmark for Procedural Knowledge Reasoning with Knowledge Module LearningTechnical
PLA-MGRA: Multi-Granularity and Relation-Aware Learning for Efficient and Generalizable Protein-Ligand Binding Affinity PredictionTechnical
PLUM-Net: Prototype-Induced Label Structuring for Disentangled Multimodal Representation NetworkTechnical
PLaST: Towards Paralinguistic-aware Speech TranslationTechnical
PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian SplattingTechnical
PMPGuard: Catching Pseudo-Matched Pairs in Remote Sensing Image–Text RetrievalTechnical
POLICYGRID: Causal Discovery for Adaptive Policy Optimization in Embodied Agents (Student Abstract)Technical
PPFL: A Parameter Behavior-Driven Plug-in Personalization Engine for Federated LearningTechnical
PPGPT: Transferring Next-Token Modeling from Language to PPG SignalsTechnical
PPS: An Efficient Java-based Simulator for Time-Discrete PDDL+Technical
PQDA:Policy-Aligned Q-Consistency Meets Decoupled Augmentation for Generalizable Visual RLTechnical
PRAGWORLD: A Benchmark Evaluating LLMs’ Local World Model Under Minimal Linguistic Alterations and Conversational DynamicsTechnical
PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking EstimationTechnical
PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented GenerationTechnical
PRIME: Planning and Retrieval-Integrated Memory for Enhanced ReasoningTechnical
PRIMP: PRobabilistically-Informed Motion Primitives for Efficient Affordance Learning from Demonstration (Abstract Reprint)Technical
PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch CollaborationTechnical
PROMISE: Prompt-Attentive Hierarchical Contrastive Learning for Robust Cross-Modal Representation with Missing ModalitiesTechnical
PSA-MF: Personality-Sentiment Aligned Multi-Level Fusion for Multimodal Sentiment AnalysisTechnical
PSEO: Optimizing Post-hoc Stacking Ensemble Through Hyperparameter TuningTechnical
PSPO: Prompt-Level Prioritization and Experience-Weighted Smoothing for Efficient Policy OptimizationTechnical
PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract)Technical
PUFM: Efficient Point Cloud Upsampling via Flow MatchingTechnical
PUNO: A Neural Operator Framework for Point Cloud UpsamplingTechnical
PaSE: Prototype-aligned Calibration and Shapley-based Equilibrium for Multimodal Sentiment AnalysisTechnical
Pacing Equilibria in Second-Price Auctions with Few BuyersTechnical
Pairing-free Group-level Knowledge Distillation for Robust Gastrointestinal Lesion Classification in White-Light EndoscopyTechnical
Palimpsest: Reconciling the CISS Trilemma for Incremental Nuclei SegmentationTechnical
PanFlow: Decoupled Motion Control for Panoramic Video GenerationTechnical
PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-CancerTechnical
Panda: Test-Time Adaptation with Negative Data AugmentationTechnical
PandemIQ Llama: A Domain-Adapted Foundation Model for Enhanced Pandemic IntelligenceTechnical
Pano-GS: Perception-Aware Gaussian Optimization with Gradient Consistency and Multi-Criteria Densification for High-Quality RenderingTechnical
PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic MemoryTechnical
Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark DatasetTechnical
Paper Folding Puzzles: Can Multimodal Large Language Models Perform Spatial Reasoning?Technical
ParaDySe: A Parallel Strategy Switching Framework for Dynamic Sequences in Transformer-based Large Language ModelsTechnical
ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from SpeechTechnical
Parallel Training Time-to-First-Spike Spiking Neural NetworksTechnical
Parallelizable Riemannian Alternating Direction Method of Multipliers for Non-convex Pose Graph OptimizationTechnical
Parameter Merging with Gradient-Guided Supermasks in Online Continual LearningTechnical
Parameter-, Memory-, Time-Efficient Multi-Task Dense Vision AdaptationTechnical
Parameter-Free Clustering via Self-Supervised Consensus MaximizationTechnical
Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation ModelsTechnical
Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to Q-LearningTechnical
Parameterized Abstract Interpretation for Transformer VerificationTechnical
Parametric Pareto Set Learning for Expensive Multi-Objective OptimizationTechnical
Pareto-Based Heterogeneous Knowledge Distillation for MLPs on GraphsTechnical
Pareto-Grid-Guided Large Language Models for Fast and High-Quality Heuristics Design in Multi-Objective Combinatorial OptimizationTechnical
ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models Using Pareto High-Quality DataTechnical
Partial Action Replacement: Tackling Distribution Shift in Offline MARLTechnical
Partial Fairness Awareness: Belief-Guided Strategic Mechanism for Strategic AgentsTechnical
PartialNet: Compute Less, Perform BetterTechnical
Partially Shared Concept Bottleneck ModelsTechnical
PatchET: Learning Enzyme Temperature Properties Through Patch-Based Neural ArchitecturesTechnical
Path-Constrained Haptic Motion Guidance via Adaptive Phase-Based Admittance Control (Abstract Reprint)Technical
PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational PathologyTechnical
PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language ModelsTechnical
PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational PathsTechnical
Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement LearningTechnical
Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert ReasonerTechnical
Paths Not Taken: Structure-Based Pruning in PSDD Learning and InferenceTechnical
PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient DiagnosisTechnical
Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph NetworkTechnical
PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health OrganizationsTechnical
PepCCD: A Contrastive Conditioned Diffusion Framework for Target-Specific Peptide GenerationTechnical
PerTouch: VLM-Driven Agent for Personalized and Semantic Image RetouchingTechnical
Perceive More with Less: LiDAR Point Cloud Compression at Just Recognizable Distortion for 3D Scene UnderstandingTechnical
Perceive, Act and Correct: Confidence Is Not Enough for Hyperspectral ClassificationTechnical
Perceiving the Knowledge Boundary: Uncertainty-Guided Exploration and Imagination for World ModelsTechnical
Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous DrivingTechnical
Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction MetricTechnical
PeriUn: Enhancing Unlearning by Selectively Forgetting Peripheral SamplesTechnical
Permutation Equivariant Framelet-based Hypergraph Neural NetworksTechnical
Persistent Autoregressive Mapping with Traffic Rules for Autonomous DrivingTechnical
Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMsTechnical
Persistent Instability in LLM’s Personality Measurements: Effects of Scale, Reasoning, and Conversation HistoryTechnical
Persona, Ego, Shadow, and Self: A Map of the Soul Framework for Proto-Emotional Homeostasis in AITechnical
Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression DetectionTechnical
Personalize Anything for Free with Diffusion TransformerTechnical
Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric RetrievalTechnical
Personalize Your Gaussian: Consistent 3D Scene Personalization from a Single ImageTechnical
Personalized Federated Graph-Level Clustering NetworkTechnical
Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random SketchingTechnical
Perturb Your Data: Paraphrase-Guided Training Data WatermarkingTechnical
Perturbing Best Responses in Zero-Sum GamesTechnical
Perturbing to Preserve: Defending Fragile Knowledge in Online Continual LearningTechnical
Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor AttacksTechnical
PharmaQA: Prompt-Based Molecular Representation Learning via Pharmacophore-Oriented Question AnsweringTechnical
Phased One-Step Adversarial Equilibrium for Video Diffusion ModelsTechnical
PhyPlan: Learning to Plan Tasks with Generalizable and Rapid Physical Reasoning for Embodied ManipulationTechnical
Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable LiquidsTechnical
PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving SystemsTechnical
Physical-regularized Hierarchical Generative Model for Metallic Glass Structural Generation and Energy PredictionTechnical
Physically-Based LiDAR Smoke Simulation for Robust 3D Object DetectionTechnical
Physically-Informed Flow Matching with Graph Neural Networks for Complex Fluid DynamicsTechnical
Physics Consistent World Models via Schrödinger-Bridge Optimal Transport for Computational Imaging and 3D-Consistent Video GenerationsTechnical
Physics-Aware Accelerated Unrolling Model for Sparse-View CT ReconstructionTechnical
Physics-Informed Approach for Exploratory Hamilton–Jacobi–Bellman Equations via Policy IterationsTechnical
Physics-Informed Autonomous LLM Agents for Explainable Power Electronics Modulation DesignTechnical
Physics-Informed Deformable Gaussian Splatting: Towards Unified Constitutive Laws for Time-Evolving Material FieldTechnical
Physics-Informed Koopman Neural Estimation of the Heston Model from High-Frequency ObservationsTechnical
Physics-Informed Multi-Task Learning for Battery State of Health Prediction with Uncertainty QuantificationTechnical
PhysicsCorrect: A Training-Free Approach for Stable Neural PDE SimulationsTechnical
Picking a Representative Set of Solutions in Multiobjective Optimization: Axioms, Algorithms, and ExperimentsTechnical
Piercing the Fog: Disentangling Key Features for Vision Models in Multi-Degradation ScenariosTechnical
PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model DecouplingTechnical
Pixel-level Quality Assessment for Oriented Object DetectionTechnical
Placing Any Object at Any 3D PositionTechnical
Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial OptimizationTechnical
Planning with Uncertain Action ModelsTechnical
PlantTraitNet: An Uncertainty-Aware Multimodal Framework for Global-Scale Plant Trait Inference from Citizen Science DataTechnical
Plot’n Polish: Zero-Shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion ModelsTechnical
Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent DisambiguationTechnical
Plug-and-Play Optimization for 3D Gaussian Splatting Compression: Distribution Regularization, Probabilistic Pruning and Detail CompensationTechnical
Plug-and-Play Parameter-Efficient Tuning of Embeddings for Federated RecommendationTechnical
PlugTrack: Multi-Perceptive Motion Analysis for Adaptive Fusion in Multi-Object TrackingTechnical
PocketLLM: Ultimate Compression of Large Language Models via Meta NetworksTechnical
PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMsTechnical
Point Cloud Quality Assessment via Multi-View Structure-Aware Feature FusionTechnical
Point Cloud Quantization Through Multimodal Prompting for 3D UnderstandingTechnical
Point Cloud Segmentation of Integrated Circuits Package Substrates Surface Defects Using Causal Inference: Dataset Construction and MethodologyTechnical
Point Cloud Semantic Scene Completion with Prototype-Guided TransformerTechnical
Point-SRA: Self-Representation Alignment for 3D Representation LearningTechnical
PointChain: Learning Generalizable Point Cloud Representations via Structural Chain ModelingTechnical
PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud ClassificationTechnical
PointMC: Multi-view Consistent Encoding and Center-Global Feature Fusion for Point Clouds UnderstandingTechnical
PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAMTechnical
Points Meet Pixels: Bridging 2D Vision-Language Model and 3D Perception Gaps for Point Cloud Quality AssessmentTechnical
Poisoned Distillation: Injecting Backdoors into Distilled Datasets Without Raw Data AccessTechnical
Poisoning with a Pill: Circumventing Detection in Federated LearningTechnical
Polarity-Aware Probing for Quantifying Latent Alignment in Language ModelsTechnical
Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image DemosaickingTechnical
Policy Newton Methods for Distortion RiskmetricsTechnical
Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic SystemsTechnical
Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement LearningTechnical
Polysemic Semantic Instance Network for Cross-Modal HashingTechnical
PortfolioPilot: An Agentic Platform for Financial Portfolio Management Algorithm Development and EvaluationTechnical
PortraitSR: Artist-Inspired Prior Learning for Progressive Face Super-ResolutionTechnical
PosPrune: Visual Token Pruning with Positional Bias Correction for Efficient Large Vision-Language ModelsTechnical
Position Fair Mechanisms Allocating Indivisible GoodsTechnical
Positional Bias in Multimodal Embedding Models: Do They Favor the Beginning, the Middle, or the End?Technical
Positional Cognitive Specialization: Where Do LLMs Learn to Comprehend and Speak Your Language?Technical
Positive Definite Sparse Covariance Estimation via Dual Space OptimizationTechnical
Post Training Quantization for Efficient Dataset CondensationTechnical
Post-Hoc Refinement for Multitask Symbolic Regression via Consensus-Accelerated Shapley AnalysisTechnical
PosterVerse: A Full-Workflow Framework for Commercial-Grade Poster Generation with HTML-Based Scalable TypographyTechnical
Posterior Label Smoothing for Node ClassificationTechnical
Potent but Stealthy: Rethink Profile Pollution Against Sequential Recommendation via Bi-Level Constrained Reinforcement ParadigmTechnical
Potential Outcome Rankings for Counterfactual Decision MakingTechnical
PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network StructureTechnical
Practical Global and Local Bounds in Gaussian Process Regression via ChainingTechnical
Practical, Utilitarian Algorithm ConfigurationTechnical
Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference ModelTechnical
Pre-Trained Video Generative Models as World SimulatorsTechnical
Predict and Resist: Long-Term Accident Anticipation Under Sensor NoiseTechnical
Predicting Emergent Tool Use in LLMs Before It Emerges: A Proxy PerspectiveTechnical
Predicting Session Termination and Retention on X from Fine-Grained Interaction Logs (Student Abstract)Technical
Predicting Video Slot Attention Queries from Random Slot-Feature PairsTechnical
Predicting the Future by Retrieving the PastTechnical
Prediction of Hospital Associated Infections During Continuous Hospital StaysTechnical
Predictive Display for Teleoperation Based on Vector Fields Using Lidar-Camera Fusion (Abstract Reprint)Technical
Preference Elicitation for Step-Wise Explanations in Logic PuzzlesTechnical
Preference Is More than Comparisons: Rethinking Dueling Bandits with Augmented Human FeedbackTechnical
Preference Optimization via Contrastive Divergence: Your Policy Is Secretly an NLL EstimatorTechnical
Preference Robustness for DPO with Applications to Public HealthTechnical
PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained TransformerTechnical
Preserving Topological and Geometric Embeddings for Point Cloud RecoveryTechnical
PressTrack-HMR: Pressure-Based Top-Down Multi-Person Global Human Mesh RecoveryTechnical
PriAgent: A Collaborative Multi-Agent Framework for Auditing Android Privacy ComplianceTechnical
Pricing Online LLM Services with Data-Calibrated Stackelberg Routing GameTechnical
Primary Visual Cortex Inspired Point Cloud Analysis FrameworkTechnical
Principled Analysis of Deep Reinforcement Learning Evaluation and Design ParadigmsTechnical
Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into PlansTechnical
Prior Refinement Is Better: Diffusion-Driven Graph Harmonization for Federated Graph LearningTechnical
PriorDrive: Enhancing Online HD Mapping with Unified Vector PriorsTechnical
PriorRG: Prior-Guided Contrastive Pre-training and Coarse-to-Fine Decoding for Chest X-ray Report GenerationTechnical
Priority-Based Graph-Enhanced Reinforcement Learning for Robust Analog Circuit OptimizationTechnical
PrivSV: Differentially Private Steering Vector for Large Language ModelsTechnical
Privacy Auditing of Multi-Domain Graph Pre-Trained Model Under Membership Inference AttacksTechnical
Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference AttackTechnical
Privacy Preserving In-Context-Learning Framework for Large Language ModelsTechnical
Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor DataTechnical
Privacy-Preserving Argumentative Explanations (Student Abstract)Technical
Privacy-protected Retrieval-Augmented Generation for Knowledge Graph Question AnsweringTechnical
Private Frequency Estimation via Residue Number SystemsTechnical
ProAR: Probabilistic Autoregressive Modeling for Molecular DynamicsTechnical
ProBench: Benchmarking GUI Agents with Accurate Process InformationTechnical
ProCAST: A Projection Framework for Coupled Aggregation Constrained Multivariate Time Series ForecastingTechnical
ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer AccelerationTechnical
ProCrop: Learning Aesthetic Image Cropping from Professional CompositionsTechnical
ProEthica: A Professional Role Based Ethical Analysis Tool Using LLM-Orchestrated, Ontology Supported Case Based ReasoningTechnical
ProFuser: Progressive Fusion of Large Language ModelsTechnical
ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offsTechnical
ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD GeneralizationTechnical
ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-LabelingTechnical
ProRec-Video: Guiding Hierarchical Interest Transitions for Proactive Short Video Recommendation with Dynamic Feedback AdaptationTechnical
ProRefine: Inference-Time Prompt Refinement with Textual Feedback (Student Abstract)Technical
Proactive Constrained Policy Optimization with Preemptive PenaltyTechnical
ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating BiasTechnical
Probabilistic Deformation Consistency for Unsupervised Shape MatchingTechnical
Probabilistic Hash Embeddings for Online Learning of Categorical FeaturesTechnical
Probabilistic Hierarchical Goal Network Planning with UCTTechnical
Probabilistic Safety Verification of Neural Policies via Predicate AbstractionTechnical
Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language ModelsTechnical
Probability Distribution Alignment and Low-Rank Weight Decomposition for Source-Free Domain Adaptive Brain DecodingTechnical
Probing EFX via PMMS: (Non-)Existence Results in Discrete Fair DivisionTechnical
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward ModelsTechnical
Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language ModelTechnical
ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge GraphsTechnical
Progressive Multi-modal Knowledge Distillation for Multi-spectral Object Re-identificationTechnical
Prometheus: Unsupervised Discovery of Phase Transitions and Order Parameters in the 2D Ising Model Using Variational Autoencoders (Student Abstract)Technical
Promises Made, Promises Kept: Safe Pareto Improvements via Ex Post Verifiable CommitmentsTechnical
Promoting Efficient Reasoning with Verifiable Stepwise RewardTechnical
PromptEmo: Learning Emotion with Bilateral Textual Prompts in Multi-Domain Open-set ScenariosTechnical
PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt MixturesTechnical
Prompting Adversarial Transferability via Path Flatness AttackTechnical
Promptus: Can Prompt Streaming Replace Video StreamingTechnical
Proof Systems That Tightly Characterise Model Counting AlgorithmsTechnical
Proof Systems for Tensor-based Model CountingTechnical
ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse AutoencodersTechnical
Prototype Entropy Alignment: Reinforcing Structured Uncertainty in LLM ReasoningTechnical
Prototype-Based Semantic Consistency Alignment for Domain Adaptive RetrievalTechnical
Prototype-Driven Active Domain Adaptation with Density ConsiderationTechnical
Prototype-Guided Supervision for Graph Learning with Noisy and Sparse LabelsTechnical
Provably Data-Driven Projection Method for Quadratic ProgrammingTechnical
Provably Efficient Multi-Objective Bandit Algorithms Under Preference-Centric CustomizationTechnical
Proxy Zero-Shot Hashing with Multimodal Fusion via Stable DiffusionTechnical
ProxyTTT: Proxy-driven Test-Time Training for Multi-modal Re-identificationTechnical
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude CompensationTechnical
Prune4Web: DOM Tree Pruning Programming for Web AgentTechnical
Pseudo Multi-view K-means ClusteringTechnical
Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural NetworksTechnical
PsyPARSE: Retrieval-Augmented Slow Thinking for Personalized Empathetic CounselingTechnical
Public Goods Games in Directed Networks with Constraints on SharingTechnical
PulseMind: A Multi-Modal Medical Model for Real-World Clinical DiagnosisTechnical
PurMM: Attention-Guided Test-Time Backdoor Purification in Multimodal Large Language ModelsTechnical
Pushing Rendering Boundaries: Hard Gaussian SplattingTechnical
Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained KnowledgeTechnical
Putting Fair Division on the MapTechnical
Q Cache: Visual Attention Is Valuable in Less than Half of Decode Layers for Multimodal Large Language ModelTechnical
Q-MoFusion: A Quantum Classifier for Masquito Species Classification (Student Abstract)Technical
Q-ROAR: Outlier-Aware Rescaling for RoPE Position Interpolation in Quantized Long-Context LLMs (Student Abstract)Technical
QAPNet: A Quantum-Attentive Patchwise Network for Robust Medical Image Classification Under Noisy InputsTechnical
QRShield: Exploiting Vulnerabilities of Latent Diffusion Models for Preventing AI Art PlagiarismTechnical
QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpressionTechnical
QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel GenerationTechnical
QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit SwitchingTechnical
QuMAB: Query-based Multi-annotator Behavior Pattern LearningTechnical
Qualitative Analysis of ω-Regular Objectives on Robust MDPsTechnical
Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and DetectionTechnical
Quality-aware and Soft Consistency Driven Representation Fusion for Incomplete Multi-view Multi-label ClassificationTechnical
QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy ExpansionTechnical
QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-ResolutionTechnical
Quantifying and Improving Adaptivity in Conformal Prediction Through Input TransformationsTechnical
Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive SimulationTechnical
Quantum Algorithms for Spectral SumsTechnical
Quantum Lipschitz BanditsTechnical
Quantum Non-Linear Bandit OptimizationTechnical
Quantum Transformer for Molecular Learning: Multi-Configuration Ground-State Energy PredictionTechnical
Query-Efficient Domain Knowledge Stealing Against Large Language ModelsTechnical
Query-Routed Activation Editing with Truth-hierarchical Preference OptimizationTechnical
QueryAligner: Customizing User Query to Match LLMs Preferences for Better Intent RecognitionTechnical
QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction DetectionTechnical
QueryGym: Step-by-Step Interaction with Relational DatabasesTechnical
Quiet Feature Learning in Algorithmic TasksTechnical
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video ComprehensionTechnical
R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual ScenariosTechnical
R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series ModelsTechnical
RAA: Achieving Interactive Remove/Add Anything via Fully Synthetic DataTechnical
RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot DetectionTechnical
RAC-DMVC: Reliability-Aware Contrastive Deep Multi-View Clustering Under Multi-Source NoiseTechnical
RAG-Enhanced Collaborative LLM Agents for Drug DiscoveryTechnical
RAG-R1:Incentivizing the Search and Reasoning Capabilities of LLMs Through Multi-Query ParallelismTechnical
RAGAR: Retrieval Augmented Personalized Image Generation Guided by RecommendationTechnical
RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented GenerationTechnical
RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image WatermarkingTechnical
RAPID: A Rapid Prototyping Platform for Industrial AutomationTechnical
RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video AttentionTechnical
RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow MatchingTechnical
RCAFlow: A Workflow-Informed Hierarchical Planning Multi-Agent System for Root Cause AnalysisTechnical
RCMoE: A Communication-Efficient Random Compression Framework for Resource-Constrained Mixture-of-Experts TrainingTechnical
RCP-LO: A Relative Coordinate Prediction Framework for Generalizable Deep LiDAR OdometryTechnical
RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as PriorTechnical
REACT-LLM: A Benchmark for Evaluating LLM Integration with Causal Features in Clinical Prognostic TasksTechnical
REACTION: Parameter-Efficient Learning for RecommendationTechnical
READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head GenerationTechnical
REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question AnsweringTechnical
RECoRD: A Multi-Agent LLM Framework for Reverse Engineering Codebase to Relational DiagramTechnical
REFO: Reinforced Evolutionary Faithfulness Optimization for Large Language ModelsTechnical
REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech TranslationTechnical
REMEDIS: A Clinical AI Framework for Retinal Disease Diagnosis with Explainable Fundus Image AnalysisTechnical
REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output FeatureTechnical
RENEW: Risk- and Energy-Aware Navigation in Dynamic WaterwaysTechnical
RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven AgentsTechnical
RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract)Technical
RESTL: Reinforcement Learning Guided by Multi-Aspect Rewards for Signal Temporal Logic TransformationTechnical
RFF-TTA: Physical Information-Aware Prototype for Temporally Varying RF Fingerprinting Online Test-Time-AdaptationTechnical
RFI: Rectified Flow Intervention for Mitigating Object Hallucination in Large Vision-Language ModelsTechnical
RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QATechnical
RFNNS: Robust Fixed Neural Network Steganography with Universal Text-to-Image ModelsTechnical
RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot ManipulationTechnical
RI-Loss: A Learnable Residual-Informed Loss for Time Series ForecastingTechnical
RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data SelectionTechnical
RIS-LAD: A Benchmark and Model for Referring Image Segmentation in Low-Altitude Drone ImageryTechnical
RL-Studio: A System for Multi-Phase Reinforcement Learning ExperimentationTechnical
RL-U2Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart SegmentationTechnical
RLKD: Distilling LLMs’ Reasoning via Reinforcement LearningTechnical
RLMR: Reinforcement Learning with Mixed Rewards for Creative WritingTechnical
RLSLM: A Hybrid Framework Combining Reinforcement Learning and a Rule-based Social Locomotion Model for Socially-aware NavigationTechnical
RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language ModelsTechnical
RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence MitigatorTechnical
RMLer: Synthesizing Novel Objects Across Diverse Categories via Reinforcement Mixing LearningTechnical
RMO: Towards Better LLM Alignment via Reshaping Reward Margin DistributionsTechnical
RMSAGen: Integrating Multiple Sequence Alignment for Function RNA DesignTechnical
ROVER: Robust Generative Continual Identity Unlearning Against Relearning AttacksTechnical
RPE-PAD: Relative Pose Estimation for Pose-agnostic Anomaly DetectionTechnical
RPGen: Robust and Differentially Private Synthetic Image GenerationTechnical
RPM-MCTS: Knowledge-Retrieval as Process Reward Model with Monte Carlo Tree Search for Code GenerationTechnical
RPTS: Tree-Structured Reasoning Process Scoring for Faithful Multimodal EvaluationTechnical
RS2-SAM2: Customized SAM2 for Referring Remote Sensing Image SegmentationTechnical
RSA-CR: Resisting Shilling Attacks in Citation Recommendation via Dumbbell Inductive LearningTechnical
RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited LabelsTechnical
RSPlace: Rotation Sensing Macro Placement via Bidirectional Tree ExpansionTechnical
RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing ImagesTechnical
RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single ImageTechnical
RTMol: Rethinking Molecule-text Alignment in a Round-trip ViewTechnical
RUL-QMoE: Multiple Non-crossing Quantile Mixture-of-Experts for Probabilistic Remaining Useful Life Predictions of Varying Battery MaterialsTechnical
RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning ReliabilityTechnical
RaLD: Generating High-Resolution 3D Radar Point Clouds with Latent DiffusionTechnical
RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point CloudsTechnical
RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket AnalysisTechnical
Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds (Abstract Reprint)Technical
Radar-APLANC: Unsupervised Radar-based Heartbeat Sensing via Augmented Pseudo-Label and Noise ContrastTechnical
RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-wave Point Cloud SequenceTechnical
RadarMP: Motion Perception for 4D mmWave Radar in Autonomous DrivingTechnical
Rademacher Complexity for Distributionally Robust LearningTechnical
Random Amalgamation of Adapters for Flatter Loss Landscapes: Towards Class-Incremental Learning with Better StabilityTechnical
Random is Faster than Systematic in Multi-Objective Local SearchTechnical
RankList – a Listwise Preference Learning Framework for Predicting Subjective PreferencesTechnical
RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and TreatmentTechnical
RatioMorph: Controllable Diffusion Framework for Automotive Viewpoint and Proportion Manipulation in Vehicle DesignTechnical
RatioSketch: Towards More Accurate Frequency Estimation in Data Streams via a Lightweight Neural NetworkTechnical
Rational Revision of Group IntentionsTechnical
RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object DetectionTechnical
RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly DetectionTechnical
Re-SpS: A Reinforcement Learning Approach to Speculative SamplingTechnical
Re-architecting Personalized Federated Learning for Demanding Edge EnvironmentsTechnical
ReACT: Reward-informed Autoregressive Decision CAD TransformerTechnical
ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided AlignmentTechnical
ReBoot: Encrypted Training of Deep Neural Networks with CKKS BootstrappingTechnical
ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language ModelsTechnical
ReCast: Reliability-aware Codebook-assisted Lightweight Time Series ForecastingTechnical
ReCode: Updating Code API Knowledge with Reinforcement LearningTechnical
ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report GenerationTechnical
ReLUPruner: Rethinking ReLU Importance with Taylor Expansion for Efficient Private InferenceTechnical
ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video RetrievalTechnical
ReaSon: Reinforced Causal Search with Information Bottleneck for Video UnderstandingTechnical
Real Garment Benchmark (RGBench): A Comprehensive Benchmark for Robotic Garment Manipulation Featuring a High-Fidelity Scalable SimulatorTechnical
Real Noise Decoupling for Hyperspectral Image DenoisingTechnical
Real-Time Path Planning for UAVs in Windy Environments Without Computational Fluid DynamicsTechnical
Real-time 3D Object Detection with Inference-Aligned LearningTechnical
RealNet: Efficient and Unsupervised Detection of AI-Generated Images via Real-Only Representation LearningTechnical
RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation LearningTechnical
RealUHR: Harnessing Patch-Cascade Flows for Photorealistic Ultra-High-Resolution SynthesisTechnical
RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World UsersTechnical
Realism Control One-step Diffusion for Real-world Image Super ResolutionTechnical
Realist and Pluralist Conceptions of Intelligence and Their Implications on AI ResearchTechnical
Realistic Curriculum Reinforcement Learning for Autonomous and Sustainable Marine Vessel NavigationTechnical
Realistic Face Reconstruction from Facial Embeddings via Diffusion ModelsTechnical
Reality vs Counterfactual: Multi-World Contrastive Reinforcement Learning for Enhancing MLLM’s Theory of Mind in Egocentric VideosTechnical
Reason2Attack: Jailbreaking Text-to-Image Models via LLM ReasoningTechnical
ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small ModelsTechnical
Reasoning About the Unsaid: Misinformation Detection with Omission-Aware Graph InferenceTechnical
Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural NormsTechnical
Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language UnderstandingTechnical
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data ContaminationTechnical
Reasoning via Implicit Self-supervised Emergence for Instruction SegmentationTechnical
Reasoning with Exploration: An Entropy PerspectiveTechnical
RecCocktail: A Generalizable and Efficient Framework for LLM-Based RecommendationTechnical
RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender SystemsTechnical
ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot PerceiverTechnical
Reconcile Gradient Modulation for Harmony Multimodal LearningTechnical
Reconfiguring Proportional CommitteesTechnical
Reconstruction Attack-Resistant Inference Paradigm for LLM Cloud ServicesTechnical
Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian SplattingTechnical
Recovering Coherent Affective Patterns: Addressing Modality Missing in Multimodal Sentiment AnalysisTechnical
Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with PromptsTechnical
Rectified Noise: A Generative Model Using Positive-incentive NoiseTechnical
Rectify Evaluation Preference: Improving LLMs’ Critique on Math Reasoning via Perplexity-aware Reinforcement LearningTechnical
Recursive Causal Discovery (Abstract Reprint)Technical
Reducing Alert Fatigue Through AI Ranking: A Deployed Public Health Data Monitoring SystemTechnical
Reducing Goal State Divergence with Environment DesignTechnical
Reducing the Scope of Language ModelsTechnical
Redundancy-optimized Multi-head Attention Networks for Multi-view Multi-label Feature SelectionTechnical
Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and PrunableTechnical
RefAdGen: High-Fidelity Advertising Image GenerationTechnical
RefLens: End-to-End Evidence-Grounded Citation Verification with LLM AgentsTechnical
RefRea: Reference-Guided Reasoning with Meta-Cognition for Accurate Language Model AgentsTechnical
RefSTAR: Blind Face Image Restoration with Reference Selection, Transfer, and ReconstructionTechnical
Reference Recommendation Based Membership Inference Attack Against Hybrid-Based Recommender SystemsTechnical
RefiDiff: Progressive Refinement Diffusion for Efficient Missing Data ImputationTechnical
Refine and Align: Confidence Calibration Through Multi-Agent Interaction in VQATechnical
Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality AssessmentTechnical
Refine3D: Scene-Adaptive Reference Point Refinement for Sparse 3D Object DetectionTechnical
RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly DetectionTechnical
Refinement Contrastive Learning of Cell–Gene Associations for Unsupervised Cell Type IdentificationTechnical
RefleXNet: Targeted Self-Reflection for Accurate Chest X-ray ReportingTechnical
Reflect Then Learn: Active Prompting for Information Extraction Guided by Introspective ConfusionTechnical
ReflexDiffusion: Reflection-Enhanced Trajectory Planning for High-lateral-acceleration Scenarios in Autonomous DrivingTechnical
Region-Point Joint Representation for Effective Trajectory Similarity LearningTechnical
RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright ProtectionTechnical
RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document UnderstandingTechnical
Regression over Classification: Assessing Image Aesthetics via Multimodal Large Language ModelsTechnical
Regressor-guided Diffusion Model for De Novo Peptide Sequencing with Explicit Mass ControlTechnical
Regular Games -- an Automata-Based General Game Playing LanguageTechnical
Reimagining Anomalies: What If Anomalies Were Normal?Technical
Reinforce Trustworthiness in Multimodal Emotional Support SystemTechnical
Reinforced Rate Control for Neural Video Compression via Inter-Frame Rate–Distortion AwarenessTechnical
Reinforcement Learning Enhanced Muti-hop Reasoning for Temporal Knowledge Question AnsweringTechnical
Reinforcement Learning Without Explicit Rewards: Theory and PracticeTechnical
Reinforcement Learning with Fuzzy Human Attention-Guided Graph for Heterogeneous Multiagent SystemsTechnical
Rejoining Precious Artifacts: Efficiently Bone Stick Rejoining Based Massive Fragment Images by Contour, Script, and TextureTechnical
RelaCtrl: Relevance-Guided Efficient Control for Diffusion TransformersTechnical
Relation-R1: Progressively Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relation ComprehensionTechnical
Relational Verification for Cost-Aware Quantum Program OptimizationTechnical
Relative Advantage Debiasing for Watch-Time Prediction in Short-Video RecommendationTechnical
Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement LearningTechnical
Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud UnderstandingTechnical
Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAGTechnical
Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience StrategiesTechnical
Remodeling Semantic Relationships in Vision-Language Fine-TuningTechnical
RemoteReasoner: Towards Unifying Geospatial Reasoning WorkflowTechnical
Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse EngineeringTechnical
Renormalization Group Guided Tensor Network Structure SearchTechnical
Rep Deep & Machine Learning: Exemplar-Free Continual Video Action Recognition via Slow-Fast Collaborative LearningTechnical
Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message Passing LimitTechnical
Requirements for Aligned, Dynamic Resolution of Conflicts in Operational ConstraintsTechnical
Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution InputTechnical
ResMAS: Resilience Optimization in LLM-based Multi-agent SystemsTechnical
ResNet-GA: Evolutionary Deep Learning Models for Adversarial Defense (Student Abstract)Technical
ResProto-FD: Visual-Language Residual Prototype Sets for Generalized Face Forgery DetectionTechnical
Rescind: Countering Image Misconduct in Biomedical Publications with Vision-Language and State-Space ModelingTechnical
RescueLens: LLM-Powered Triage and Action on Volunteer Feedback for Food RescueTechnical
Resilience Inference for Supply Chains with Hypergraph Neural NetworkTechnical
Resilience in Ambient Multi-Agent LLMs via Decentralized Bio-Autonomic Control and Immune-Inspired Anomaly DetectionTechnical
Resilient UAV Swarm with Fast Connectivity Recovery and Extensive CoverageTechnical
Resolving Predictive Multiplicity for the Rashomon SetTechnical
Resource Efficient Sleep Staging via Multi-Level Masking and Prompt LearningTechnical
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language ModelsTechnical
Responsible Mechanism DesignTechnical
Retaliatory Attacks Against Federated Unlearning via Data LeakageTechnical
Rethink Representation Learning for Questionnaire DataTechnical
Rethinking AI: From Functions to FunctorsTechnical
Rethinking Bias in Generative Data Augmentation for Medical AI: A Frequency Recalibration MethodTechnical
Rethinking Crystal Symmetry Prediction: A Decoupled PerspectiveTechnical
Rethinking Deep Alignment Through the Lens of Incomplete Safety LearningTechnical
Rethinking Direct Preference Optimization in Diffusion ModelsTechnical
Rethinking Explanation Evaluation Under the Retraining SchemeTechnical
Rethinking Flow and Diffusion Bridge Models for Speech EnhancementTechnical
Rethinking Irregular Time Series Forecasting: A Simple Yet Effective BaselineTechnical
Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation PerspectiveTechnical
Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and RelabelingTechnical
Rethinking Membership Inference Attacks for CLIPTechnical
Rethinking Multi-Instance Learning Through Graph-Driven Fusion: A Dual-Path Approach to Adaptive RepresentationTechnical
Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction PerspectiveTechnical
Rethinking Open-world Prompt Tuning: A Systematic Framework for Evaluation and OptimizationTechnical
Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric PerspectiveTechnical
Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness TuningTechnical
Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for ExplanationsTechnical
Rethinking Surgical Smoke: A Smoke-Type-Aware Laparoscopic Video Desmoking Method and DatasetTechnical
Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative ApproachTechnical
Rethinking Video-Language Model from the Language Input PerspectiveTechnical
Rethinking Visual Token Reduction in LVLMs Under Cross-Modal MisalignmentTechnical
Rethinking the Dark Knowledge and Kullback-Leibler Divergence Loss in Knowledge Distillation Under Capacity MismatchingTechnical
Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault ToleranceTechnical
Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment PerspectiveTechnical
Rethinking the Spatio-Temporal Alignment of End-to-End 3D PerceptionTechnical
RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM AgentsTechnical
Retrieval-driven Reasoning for Deliberative Visual ClassificationTechnical
Retriever Encoder Selection Matters for In-Context Learning-based Medical SegmentationTechnical
RetroLM: Retrieval-Augmented KVs for Long-Context ProcessingTechnical
RetrySQL: Text-to-SQL Training with Retry Data for Self-Correcting Query GenerationTechnical
Revealing POMDPs: Qualitative and Quantitative Analysis for Parity ObjectivesTechnical
Revealing the Invisible: Latent Structure Modeling for Semantically Consistent Cloud RemovalTechnical
Revisiting (Un)Fairness in Recourse by Minimizing Worst-Case Social BurdenTechnical
Revisiting Attention in the Dark for Low-Light Person Re-IdentiffcationTechnical
Revisiting Conjunctive Query Entailment for STechnical
Revisiting Contrastive Learning in Collaborative Filtering via Parallel Graph FiltersTechnical
Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video ModelsTechnical
Revisiting Differentiable Structure Learning: Inconsistency of L1 Penalty and BeyondTechnical
Revisiting Downsampling in Semantic Segmentation: Fighting Aliasing with Dynamic Gaussian and Gabor Frequency FiltersTechnical
Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control KnobTechnical
Revisiting MLLM Based Image Quality Assessment: Errors and RemedyTechnical
Revisiting Network Inertia: Dynamic Inertia Inhibition Coupled Multidimensional Periodicity for Infrared and Visible Image FusionTechnical
Revisiting the Canonicalization for Fast and Accurate Crystal Tensor Property PredictionTechnical
Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish ViewTechnical
Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series ForecastingTechnical
Reward Model Evaluation via Automatically-Ranked Policy AlignmentTechnical
Reward Redistribution via Gaussian Process Likelihood EstimationTechnical
RflyPano: A Panoramic Benchmark for Ultra-low Altitude UAV Localization Powered by RflySimTechnical
Richer Representations for Neural Algorithmic Reasoning via Auxiliary ReconstructionTechnical
RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph OptimizationTechnical
Riemannian Manifold Learning for Stackelberg Games with Neural Flow RepresentationsTechnical
Right Branches Matter in Failure-based Variable Ordering HeuristicsTechnical
Right Looks, Wrong Reasons: Compositional Fidelity in Text-to-Image GenerationTechnical
RipAlert: A Future-Frame-Aware Framework for Rip Current Forecasting and Early AlertingTechnical
Ripple Shapley: Data Influence Attribution in One Federated Training RunTechnical
Risk Atlas Nexus: A System for Managing AI RisksTechnical
Risk-Aware Bilingual Spoken Dialogue for Campus Mental Health SupportTechnical
Risk-Sensitive Exponential Actor CriticTechnical
RiverScope: High-Resolution River Masking DatasetTechnical
RoS-Guard: Robust and Scalable Online Change Detection with Delay-Optimal GuaranteesTechnical
RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language ModelsTechnical
RoSE: A Role Correlation Structure-Enhanced Model for Multi-Event Argument ExtractionTechnical
RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation SystemTechnical
RobusTor3D: Robust Multimodal 3D Object Detector for Autonomous Driving by Vision-Language Knowledge BlendingTechnical
Robust Adaptive Multi-Step Predictive Shielding (Student Abstract)Technical
Robust Causal Discovery Under Imperfect Structural ConstraintsTechnical
Robust Decentralized Multi-armed Bandits: From Corruption-Resilience to Byzantine-ResilienceTechnical
Robust Detection of Synthetic Tabular Data Under Schema VariabilityTechnical
Robust Domain Adaptive Hashing via Structural Noise Modeling and CorrectionTechnical
Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language InstructionsTechnical
Robust High-Order Tensor Compressive Sensing Based on M-EstimatorsTechnical
Robust Integrative Analysis of Multi-omics Datasets via Nuclear-norm MaximizationTechnical
Robust Lazy Conflict Detection via Multi-Conflict Extraction and Genetic Diversity ControlTechnical
Robust Learning from Noisily Labeled Long-Tailed Data via Fairness RegularizerTechnical
Robust Long-Term Test-Time Adaptation for 3D Human Pose Estimation Through Motion DiscretizationTechnical
Robust Multiagent Combinatorial Path FindingTechnical
Robust Noise Modeling for Spike Camera via Time-Interval Quantification and Spike-DSLR Multimodal Dataset in Low-Light ImagingTechnical
Robust Out-of-Order Retrieval for Grid-Based Storage at Maximum CapacityTechnical
Robust Pedestrian Detection with Uncertain ModalityTechnical
Robust Pseudo-Labeling via Decoupled Class-Aware Filtering and Dynamic Category CorrectionTechnical
Robust SDE Parameter Estimation Under Missing Time Information SettingTechnical
Robust Semi-paired Multimodal Learning for Cross-modal RetrievalTechnical
Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent DiffusionTechnical
Robust Watermarking on Gradient Boosting Decision TreesTechnical
Robust-R1: Degradation-Aware Reasoning for Robust Visual UnderstandingTechnical
Role Hypergraph Contrastive Learning for Multivariate Time-Series AnalysisTechnical
Role Perceptual Augmented Temporal Graph Network for Related-party Transaction DetectionTechnical
RouterNet: Hierarchical Point Routing Network for Robust Vertebral Landmark Localization on AP X-ray ImagesTechnical
Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language NavigationTechnical
Runtime Safety and Reach-avoid Prediction of Stochastic Systems via Observation-aware Barrier FunctionsTechnical
R²D-LPCC: Relevance-Ranking Guided Region-Adaptive Dynamic LiDAR Point Cloud CompressionTechnical
S-D-RSM: Stochastic Distributed Regularized Splitting Method for Large-Scale Convex Optimization ProblemsTechnical
S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous ReasoningTechnical
S2-Boost: Synergistic Semantic Boosting for Coarse-to-Fine Ensemble LearningTechnical
S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything Without SupervisionTechnical
S2C: A Noise-Resistant Difference Learning Framework for Unsupervised Change Detection in VHR Remote Sensing ImagesTechnical
S2D-Align: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report GenerationTechnical
S3Net: Spatiotemporally Separated Sparse Network for Neuromorphic Vision ProcessingTechnical
S5: Scalable Semi-Supervised Semantic Segmentation in Remote SensingTechnical
SABER: Switchable and Balanced Training for Efficient LLM ReasoningTechnical
SACO: Sequence-Aware Constrained Optimization Framework for Coupon Distribution in E-commerceTechnical
SACodec: Asymmetric Quantization with Semantic Anchoring for Low-Bitrate High-Fidelity Neural Speech CodecsTechnical
SAFE: Semantic- and Frequency-Enhanced Curriculum for Cross-Domain Deepfake DetectionTechnical
SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image GenerationTechnical
SAGE: A Compositional Multi-Agent LLM Framework with Pedagogical Reasoning for Structured Collaborative Problem SolvingTechnical
SAGE: Spuriousness-Aware Guided Prompt Exploration for Mitigating Multimodal BiasTechnical
SAGE: Structured Attribute-Guided Enhancement for GZSLTechnical
SALR: Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language ModelsTechnical
SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object DetectionTechnical
SAM2-OV: A Novel Detection-Only Tuning Paradigm for Open-Vocabulary Multi-Object TrackingTechnical
SAM2MOT: A Novel Paradigm of Multi-Object Tracking by SegmentationTechnical
SAMCL: Empowering SAM to Continually Learn from Dynamic Domains with Extreme Storage EfficiencyTechnical
SAME: Spatial-Aware Multimodal Egocentric Human Pose EstimationTechnical
SAMGTD: Spatial-Aware Masked Graph Transformer-Diffusion Model for Enhanced Cell Type Deconvolution in Spatial TranscriptomicsTechnical
SAOT: An Enhanced Locality-Aware Spectral Transformer for Solving PDEsTechnical
SAPO: Self-Adaptive Process Optimization Makes Small Reasoners StrongerTechnical
SAQ-SAM: Semantically-Aligned Quantization for Segment Anything ModelTechnical
SAR-DisentDM: A Semantic-Disentangled Diffusion Model for Limited-Data SAR Image SynthesisTechnical
SAR: A Structure-Aligned Reasoning Framework for Temporal Knowledge Graph Question AnsweringTechnical
SARA: Leveraging LLM Agents and Jurisprudential Ontologies for Automated Legal ReasoningTechnical
SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech TranslationTechnical
SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early RevisionTechnical
SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic AugmentationTechnical
SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel ContextTechnical
SCALAR: Scale-wise Controllable Visual Autoregressive LearningTechnical
SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time ScalingTechnical
SCAN: Self-Calibrated AutoregressioN for High-Quality Visual GenerationTechnical
SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on SchemaTechnical
SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMsTechnical
SCORE: Semantic Collage by Optimizing Rendered ElementsTechnical
SCo-Cloud: Satellite Constellation Collaboration for Cloud-Aware Onboard-Computed Imaging and TransmissionTechnical
SCoNE: Spherical Consistent Neighborhoods Ensemble for Effective and Efficient Multi-View Anomaly DetectionTechnical
SCoUT: A Framework for Structured Stereotype Analysis in Language ModelsTechnical
SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image DerainingTechnical
SDA: Steering-Driven Distribution Alignment for Open LLMs Without Fine-TuningTechnical
SDE-HARL: Scalable Distributed Policy Execution for Heterogeneous-Agent Reinforcement LearningTechnical
SDEval: Safety Dynamic Evaluation for Multimodal Large Language ModelsTechnical
SDNet: LiDAR Semantic Scene Completion with Sparse-Dense Fusion and Input-Aware Label RefinementTechnical
SE360: Semantic Edit in 360° Panoramas via Hierarchical Data ConstructionTechnical
SEA-PACE: Semi-Supervised Underwater Image Enhancement via Gaussian Process–Assisted Self-Paced LearningTechnical
SEAP: Sparse Expert Activation Pruning Unlocks the Brainpower of Large Language ModelsTechnical
SEBSFormer: A Spectral-Enhanced Bi-Stream Transformer for Robust EEG DecodingTechnical
SEED: Spectral Entropy-Guided Evaluation of Spatial-Temporal Dependencies for Multivariate Time Series ForecastingTechnical
SEFEL: A Simple Yet Effective Framework for Fast Event LinkingTechnical
SELDON: Supernova Explosions Learned by Deep ODE NetworksTechnical
SEMC: Structure-Enhanced Mixture-of-Experts Contrastive Learning for Ultrasound Standard Plane RecognitionTechnical
SEQRET: Mining Rule Sets from Event SequencesTechnical
SERL: Self-Examining Reinforcement Learning on Open-DomainTechnical
SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Sarcasm DetectionTechnical
SFGA: Similarity-Constrained Fusion Learning for Unsupervised Anomaly Detection in Multiplex GraphsTechnical
SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated LearningTechnical
SGAT: Learning Feature Matching with Singularity-enhanced Graph Attention NetworkTechnical
SGMHand: Structure-Guided Modulation for Structure-Aware Hand InpaintingTechnical
SGMT: Social Generating with Multiview-Guided Tuning In Recommender SystemsTechnical
SGP4SR: Separated-Modality Guided User Preference Learning for Multimodal Sequential RecommendationTechnical
SGPFeat: Semantic and Geometric Priors for Multi-modal Image MatchingTechnical
SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and GrowingTechnical
SGoT-R1: Social Graph of Thought Reasoning-Enhanced Multimodal Large Language Model for Harmful Meme DetectionTechnical
SHADOW: Dynamic-Aware Credit Assignment Against Long-Horizon TasksTechnical
SHARE: Synthesizing Heterogeneous Autism-support Records into Evidence-based RecommendationsTechnical
SIAM: Towards Generalizable Articulated Object Modeling via Single Robot-Object InteractionTechnical
SICNav: Safe and Interactive Crowd Navigation Using Model Predictive Control and Bilevel Optimization (Abstract Reprint)Technical
SIDE: Surrogate Conditional Data Extraction from Diffusion ModelsTechnical
SIFThinker: Spatially-Aware Image Focus for Visual ReasoningTechnical
SIGN: Schema Induced Games for Naming (Student Abstract)Technical
SITA: A Framework for Structure-to-Instance Theorem AutoformalizationTechnical
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better InterpretabilityTechnical
SLCFormer: Spectral-Local Context Transformer with Physics-Grounded Flare Synthesis for Nighttime Flare RemovalTechnical
SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech SynthesisTechnical
SM3Det: A Unified Model for Multi-Modal Remote Sensing Object DetectionTechnical
SMART: A Surrogate Model for Predicting Application Runtime in Dragonfly SystemsTechnical
SMIDT: High-Performance Inference Framework for MoE Models with Dynamic Top-K RoutingTechnical
SMPRO: Self-Supervised Visual Preference Alignment via Differentiable Multi-Preference Multi-Group RankingTechnical
SMiLE: Provably Enforcing Global Relational Properties in Neural NetworksTechnical
SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous DataTechnical
SNN-Driven Event-Based Flow and Rotation Estimation with SO(3) RefinementTechnical
SNS-Grasp: Semantic-guided Noise Scaling for Grasp GenerationTechnical
SOAR: Semi-Supervised Open-Vocabulary Aerial Object Detection via Dual-Aware Enhanced Prior DenoisingTechnical
SODiff：Semantic-Oriented Diffusion Model for JPEG Compression Artifacts RemovalTechnical
SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language ModelsTechnical
SOMA: Feature Gradient Enhanced Affine-Flow Matching for SAR-Optical RegistrationTechnical
SOSControl: Enhancing Human Motion Generation Through Saliency-Aware Symbolic Orientation and Timing ControlTechnical
SPA: Achieving Consensus in LLM Alignment via Self-Priority OptimizationTechnical
SPAN: Benchmarking and Improving Cross-Calendar Temporal Reasoning of Large Language ModelsTechnical
SPARD: Single-step Inference with Adaptive Sampling in Residual Diffusion for Human Motion PredictionTechnical
SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward ModellingTechnical
SPEED-Q: Staged Processing with Enhanced Distillation Towards Efficient Low-Bit On-Device VLM QuantizationTechnical
SPIRAL: Symbolic LLM Planning via Grounded and Reflective SearchTechnical
SPJFNet: Self-Mining Prior-Guided Joint Frequency Enhancement for Ultra-Efficient Dark Image RestorationTechnical
SPP-SCL: Semi-Push-Pull Supervised Contrastive Learning for Image-Text Sentiment Analysis and BeyondTechnical
SPSC: Sparse and Scalable Multi-Modal 3D Occupancy Prediction for Autonomous DrivingTechnical
SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised AttentionTechnical
SRACG: A Code Generation Framework with Selective Retrieval AugmentationTechnical
SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape EvaluationTechnical
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMsTechnical
SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View ImagesTechnical
SSCL: Adversarially Guided Image Compression via Semantic and Spectral Consistency LearningTechnical
SSHPool: The Separated Subgraph-based Hierarchical PoolingTechnical
SSL-CST: Cell Segmentation for Single-Cell Spatial Transcriptome Based on Self-Supervised LearningTechnical
SSR-SAM: Retrieval-Style Segment Anything Model for Semi-Supervised Ultra-High-Resolution Image SegmentationTechnical
SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised SegmentationTechnical
SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature PredictionTechnical
ST-LLM: Spatial Transcriptomics Embedding with Large Language ModelsTechnical
ST-SAM: Multimodal Scene Text Segmentation with Dense Visual and Sparse Textual Prompts via SAMTechnical
ST-TPP: Learning Semi-Transductive Temporal Point Processes with Gromov-Wasserstein Barycentric RegularizationTechnical
ST-VLM: A Spatial-to-Image Multimodal Spatial-Temporal Prediction Framework with Vision-Language ModelTechnical
STACK: Adversarial Attacks on LLM Safeguard PipelinesTechnical
STAR-1: Safer Alignment of Reasoning LLMs with 1K DataTechnical
STEAMROLLER: A Multi-Agent System for Inclusive Automatic Speech Recognition for People Who StutterTechnical
STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in VisionTechnical
STEP-Nav: Spatial-Temporal Efficient Visual Token Pruning for Vision-and-Language Navigation with Large Language ModelsTechnical
STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-IdentificationTechnical
STOLA: Self-Adaptive Touch-Language Framework for Tactile Commonsense Reasoning in Open-Ended ScenariosTechnical
STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving ScenesTechnical
STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning ModelsTechnical
STrans: Spontaneous Architecture Evolution for Adaptive Time Series ForecastingTechnical
SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action RecognitionTechnical
SVD-NO: Learning PDE Solution Operators with SVD Integral KernelsTechnical
SVGL: Scale-Variable Graph Learning in Model Space for Multivariate Time Series ClassificationTechnical
SWIFT：A General Sensitive Weight Identification Framework for Fast Sensor-Transfer PansharpeningTechnical
S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal ForecastingTechnical
Safe Multi-Agent Reinforcement Learning via Distributional Safety Critic and Maximum Entropy OptimizationTechnical
Safe Multi-agent Reinforcement Learning with Natural Language ConstraintsTechnical
Safe RAG by RAG: Untying the Bell That RAG Rang with the RAG HandTechnical
Safe Reinforcement Learning for Trustworthy AI: Theory, Algorithms, and ApplicationsTechnical
SafeLens: Segment-Level Hate Speech Detection in Online VideosTechnical
SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred TrajectoriesTechnical
SafeNLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database InterfacesTechnical
SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained KnowledgeTechnical
SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent CommunicationTechnical
Safety Alignment of Large Language Models via Contrasting Safe and Harmful DistributionsTechnical
SafetyReminder: Reviving Delayed Safety Awareness of Vision-Language Models to Defend Against Jailbreak AttacksTechnical
SageLM: A Multi-aspect and Explainable Large Language Model for Speech JudgementTechnical
SalDiff-DTM: A Novel Dual-Temporal Modulated Diffusion Model for Omnidirectional Images Scanpath PredictionTechnical
Salvador Urban Network Transportation (SUNT): A Landmark Spatiotemporal Dataset for Public Transportation (Abstract Reprint)Technical
Sample Weighted Incomplete Multimodal Clustering Based on Graph Coarsening Label ExtractionTechnical
Sample-and-Search: An Effective Algorithm for Learning-Augmented k-Median Clustering in High DimensionsTechnical
Sample-specific Modality Diagnosis and Cross-modal Enhancement for Incomplete Multimodal RepresentationsTechnical
Sampling Control for Imbalanced Calibration in Semi-Supervised LearningTechnical
Sampling-Free Uncertainty Quantification via Hidden State Dynamics in Language ModelsTechnical
SampurNER: Fine-Grained Named Entity Recognition Dataset for 22 Indian LanguagesTechnical
Sarcopenia Assessment Model Based on Dual-Source Modal GraphTechnical
Sat2Flow: A Structure-Aware Diffusion Framework for Human Flow Generation from Satellite ImageryTechnical
SatSolarCast: A Flexible Framework for Multimodal Solar Irradiance Forecasting via Memory-Alignment LearningTechnical
Satellite-Text-Prompted Large Language Model for Photovoltaic Power ForecastingTechnical
SatireDecoder: Visual Cascaded Decoupling for Enhancing Satirical Image ComprehensionTechnical
Satisficing and Optimal Generalised Planning via Goal RegressionTechnical
Save, Revisit, Retain: A Scalable Framework for Enhancing User Retention in Large-Scale Recommender SystemsTechnical
Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration CodingTechnical
Scalable Air-Quality Sensor Placement via Gradient-Based Mutual Information MaximizationTechnical
Scalable Mixed-Integer Optimization with Neural Constraints via Dual DecompositionTechnical
Scalable Multi-Objective and Meta Reinforcement Learning via Gradient EstimationTechnical
Scalable Privacy-Preserving Neural Network Training over Z2k via RMFE-Based Packing and Mixed-Circuit ComputationTechnical
Scalable Semi-supervised Community Search via Graph Transformer on Attributed Heterogeneous Information NetworksTechnical
Scalable Solution Methods for Dec-POMDPs with Deterministic DynamicsTechnical
Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation GuaranteesTechnical
Scalable Synthesis of Formally Verified Neural Value Function for Hamilton-Jacobi Reachability Analysis (Abstract Reprint)Technical
Scalable Vision-Guided Crop Yield EstimationTechnical
Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case StudyTechnical
Scale Regularization for Stable Low-Rank AdaptationTechnical
Scale-Net: A Hierarchical U-Net Framework for Cross-Scale Generalization in Multi-Task Vehicle RoutingTechnical
Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback AgentsTechnical
Scaling Human-Centric Trustworthy Foundation Model via Advanced Reasoning and Agentic FrameworksTechnical
Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch ScenariosTechnical
Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?Technical
Scaling Law for Large Wireless ModelsTechnical
Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from TranslationTechnical
Scaling Towards the Information Boundary of Instructions through Data SynthesizingTechnical
Scaling Up AI AlignmentTechnical
Scaling Up Cooperative Multi-Agent Reinforcement Learning Through Hierarchical Heterogeneous Modular ArchitecturesTechnical
Scaling and Transferability of Annealing Strategies in Large Language Model TrainingTechnical
Scaling-up Perceptual Video Quality AssessmentTechnical
Scene Experts: Specializing in 3D Gaussian Splatting with Adaptive DecompositionTechnical
Scene-Aware Spatiotemporal Generalization: Towards Robust Temporal Action Detection Across DomainsTechnical
SceneGenesis: 3D Scene Synthesis via Semantic Structural Priors and Mesh-Guided Video-Geometry FusionTechnical
SceneJailEval: A Scenario-Adaptive Multi-Dimensional Framework for Jailbreak EvaluationTechnical
SchellingFormer: Laplacian Matrix-guided Geometric Transformer for Robust Schelling Point DetectionTechnical
Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at ScaleTechnical
Schema-Guided Event Reasoning: A Plug-and-Play Event Reasoning Framework Based on Large Language ModelsTechnical
Schema-Guided Scene-Graph Reasoning Based on Multi-Agent Large Language Model SystemTechnical
SciDataMAS: LLM-Driven MAS for Scientific Data Management (Student Abstract)Technical
SciMKG: A Multimodal Knowledge Graph for Science Education with Text, Image, Video and AudioTechnical
Scientifically-Interpretable Reasoning Network (ScIReN): Discovering Hidden Relationships in the Carbon Cycle and BeyondTechnical
Scope Delineation Before Localization: A Two-Stage Framework for Enhancing Failure Attribution in Multi-Agent SystemsTechnical
Score-Based Model for Low-Rank Tensor RecoveryTechnical
SculptDrug: A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug DesignTechnical
SeViL: Semi-supervised Vision-Language Learning with Text Prompt Guiding for Moving Infrared Small Target DetectionTechnical
SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-ComputeTechnical
Security Games with Layered Defenses: Adaptive Adversaries and Gittins IndicesTechnical
See, Rank, and Filter: Important Word-Aware Clip Filtering via Scene Understanding for Moment Retrieval and Highlight DetectionTechnical
Seeing Beyond Illusion: Generalized and Efficient Mirror DetectionTechnical
Seeing Is Believing: Grounding Long-Video Understanding in Spatio-Temporal Visual EvidenceTechnical
Seeing Is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual GroundingTechnical
Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion GuidanceTechnical
Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive LearningTechnical
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMsTechnical
Seeing the Unseen: Zooming in the Dark with Event CamerasTechnical
Seeing through the Conﬂict: Transparent Knowledge Conﬂict Handling in Retrieval-Augmented GenerationTechnical
SegDINO3D: 3D Instance Segmentation Empowered by Both Image-Level and Object-Level 2D FeaturesTechnical
SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge EnvironmentsTechnical
Segment Anything Across Shots: A Method and BenchmarkTechnical
Segment and Matte Anything in a Unified ModelTechnical
Selection of LLM Fine-Tuning Data Based on Orthogonal RulesTechnical
Selective Diffusion Distillation for Real-World High-Scale Image Super-ResolutionTechnical
Selective Weak-to-Strong GeneralizationTechnical
Self-Adaptive Graph Mixture of ModelsTechnical
Self-Correction Distillation for Structured Data Question AnsweringTechnical
Self-Enhanced Image Clustering with Cross-Modal Semantic ConsistencyTechnical
Self-Guided Planning and Repair Framework for Code Generation (Student Abstract)Technical
Self-Improving Sparse Retrieval Through Heuristic Representation Refinement and Representation-Focused LearningTechnical
Self-Indexing KVCache: Predicting Sparse Attention from Compressed KeysTechnical
Self-Interpretable Subgraph Neural Network with Deep Reinforcement Walk ExplorationTechnical
Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-TuningTechnical
Self-Regulating Cars: Automating Traffic Control in Free Flow Road NetworksTechnical
Self-Supervised Contrastive Re-Learning for Multi-Graph Multi-Label ClassificationTechnical
Self-Supervised Cross-City Trajectory Representation Learning Based on Meta-LearningTechnical
Self-Supervised Hypergraph Learning with Substructure Awareness for Hyperedge PredictionTechnical
Self-Supervised Inductive Logic ProgrammingTechnical
Self-Supervised Learning Based on Transformed Image Reconstruction for Equivariance-Coherent Feature RepresentationTechnical

AAAI accepted papers in other years

AAAI 2025 (3,478)AAAI 2024 (2,861)AAAI 2023 (2,016)AAAI 2022 (1,319)AAAI 2021 (1,653)

Looking for submission deadlines instead? See the conference deadline calendar.