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

Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive ImagingTechnical
Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object DetectionTechnical
Self-supervised Multiplex Consensus Mamba for General Image FusionTechnical
Semantic Alignment of Malicious Question Based on Contrastive Semantic Networks and Data Augmentation (Abstract Reprint)Technical
Semantic Document Derendering: SVG Reconstruction via Vision-Language ModelingTechnical
Semantic Embedding and Synthetic Augmentation for Longitudinal Survey Prediction (Student Abstract)Technical
Semantic Feature Purification for Adversarially-Aware RGB-T TrackingTechnical
Semantic Guided Part Relation-aware Network for Point Cloud CompletionTechnical
Semantic Volume: Quantifying and Detecting Both External and Internal Uncertainty in LLMsTechnical
Semantic-Augmented Image Clustering via Adaptive Multi-Modal CollaborationTechnical
Semantic-Aware Data Augmentation for Sequential RecommendationTechnical
Semantic-Aware Feature Enhancement for Partial Label LearningTechnical
Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal RetrievalTechnical
Semantic-Driven Visual Progressive Refinement for Aerial-Ground Person ReID: A Challenging Large-Scale BenchmarkTechnical
Semantic-Guided Sketch-to-RGB Image Generation via Controlled Diffusion for Improved Sketch Recognition (Student Abstract)Technical
SemanticNN: Compressive and Error-Resilient Semantic Offloading for Extremely Weak DevicesTechnical
SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic ManipulationTechnical
Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image DerainingTechnical
Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction ModelsTechnical
Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area MaskingTechnical
Semi-Supervised Regression by Preserving Ranking Relationships Between Close Unlabeled SamplesTechnical
Semi-Supervised Semantic Segmentation via Derivative Label PropagationTechnical
Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance ModelingTechnical
Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern GenerationTechnical
Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement LearningTechnical
Sensor Model Identification via Simultaneous Model Selection and State Variable Determination (Abstract Reprint)Technical
Sentient: Detecting APTs via Capturing Indirect Dependencies and Behavioral LogicTechnical
SepPrune: Structured Pruning for Efficient Deep Speech SeparationTechnical
SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical PlanningTechnical
Sequence-Free for Compound Protein Interaction PredictionTechnical
Sequential Selling with Sunk Cost BiasTechnical
ShaLa: Multimodal Shared Latent Generative ModellingTechnical
ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMsTechnical
Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development SystemsTechnical
ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition TreesTechnical
Shaping Human–AI Collaboration in Education: Effects of AI-Assisted Decision-Making Paradigms and Human–AI Decision Consistency on Pre-Service Teachers’ Psychological States and PerformanceTechnical
Shaping Parameter Contribution Patterns for Out-of-Distribution DetectionTechnical
Shaping Without Tearing: Controllable Diffeomorphic Deformations for Topology-Preserving 3D Point Cloud AugmentationTechnical
Shapley Value Approximation Based on k-Additive GamesTechnical
Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary LearningTechnical
Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time AdaptationTechnical
SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse PreferencesTechnical
Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM ReasoningTechnical
Sheaf Graph Neural Networks via PAC-Bayes Spectral OptimizationTechnical
Shedding the Facades, Connecting the Domains: Detecting Shifting Multimodal Hate Video with Test-Time AdaptationTechnical
SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large SpreadsheetsTechnical
ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge BasesTechnical
ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based AgentsTechnical
ShortageSim: Simulating Drug Shortages Under Information AsymmetryTechnical
Shortcut Learning Susceptibility in Vision Classifiers (Student Abstract)Technical
Should You Use LLMs to Simulate Opinions? Quality Checks for Early-Stage DeliberationTechnical
Shrinking the Teacher: An Adaptive Teaching Paradigm for Asymmetric EEG-Vision AlignmentTechnical
SigFusion: Unified Signal-Level Self-Supervised Learning Paradigm for Image FusionTechnical
Sign-Aware Multimodal Graph RecommendationTechnical
Signal Enhancement via Multi-view Dynamic Representation and Alignment-aware FusionTechnical
Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-IdentificationTechnical
Silenced Biases: The Dark Side LLMs Learned to RefuseTechnical
Sim-to-Real: An Unsupervised Noise Layer for Screen-Camera Watermarking RobustnessTechnical
Sim4Seg: Boosting Multimodal Multi-disease Medical Diagnosis Segmentation with Region-Aware Vision-Language Similarity MasksTechnical
SimDiff: Simpler Yet Better Diffusion Model for Time Series Point ForecastingTechnical
SimLabel: Similarity-Weighted Semi-supervision for Multi-annotator Learning with Missing LabelsTechnical
SimROD: A Simple Baseline for Raw Object Detection with Global and Local EnhancementsTechnical
Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation DiffusionTechnical
SimpleDiffusion: A Lightweight and Efficient Conditional Diffusion Model for Multi-Modal Salient Object DetectionTechnical
Simulated Rewards, Skewed Strategies: Tracing the Acquired Preference Bias in LLM-Based Dialogue PlannersTechnical
Simulating Dispute Mediation with LLM-Based Agents for Legal ResearchTechnical
Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object DetectionTechnical
Simulating Human-Like Counseling: A Path- and Scenario-Guided Framework for Psychological Support DialogueTechnical
Simulation-Driven Railway Delay Prediction: An Imitation Learning ApproachTechnical
SinBasis Networks: Matrix-Equivalent Feature Extraction for Wave-Like Optical SpectrogramsTechnical
SineLoRA∆: Sine-Activated Delta CompressionTechnical
Single-Stage fMRI-to-3D Reconstruction via Viewpoint-Aware Embedding and Hierarchical GuidanceTechnical
Situating Youth Agency in Designing AI & Art PoliciesTechnical
Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-IdentificationTechnical
Sketch-Guided Anime Hair Editing Using Multimodal Diffusion Transformer (Student Abstract)Technical
Skill Path: Unveiling Language Skills from Circuit GraphsTechnical
SkillGen: Learning Domain Skills for In-Context Sequential Decision MakingTechnical
SkipCat: Rank-Maximized Low-Rank Compression of Large Language Models via Shared Projection and Block SkippingTechnical
SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of ExpertsTechnical
SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite ImagesTechnical
Sleep-Like Replay Reduces Loss-Landscape Sharpness to Improve Generalization (Student Abstract)Technical
Slender3D: Curve-Guided Multi-View Reconstruction of Slender StructuresTechnical
SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal PresentationsTechnical
SlideTailor: Personalized Presentation Slide Generation for Scientific PapersTechnical
Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMsTechnical
SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token PruningTechnical
Small Models Exhibit Limited Answer Consistency in Repetition Trials of the Multiple-Choice MMLU-Redux and MedQA BenchmarksTechnical
Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object SegmentationTechnical
SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber WorldTechnical
SmartEyes: Plug-and-Play Event Detection for Retail Loss PreventionTechnical
SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention CollapseTechnical
SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution ImagesTechnical
SoMe: A Realistic Benchmark for LLM-based Social Media AgentsTechnical
Social Behavior as a Key to Learning-Based Multi-Agent Pathfinding Dilemmas (Abstract Reprint)Technical
Social Influence-Based Mutual Acknowledgement Token Exchange (Student Abstract)Technical
Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-Based Test OraclesTechnical
Soft Conflict-Resolution Decision Transformer for Offline Multi-Task Reinforcement LearningTechnical
Sonic4D: Spatial Audio Generation for Immersive 4D Scene ExplorationTechnical
Sonnet: Spectral Operator Neural Network for Multivariable Time Series ForecastingTechnical
Sortblock: Similarity-Aware Feature Reuse for Diffusion ModelTechnical
Sound-AI: A Pedagogical Tool for Exploring AI in Audio and Bioacoustic ResearchTechnical
Source-Free Graph Foundation Model Adaptation via Pseudo-Source ReconstructionTechnical
SpaCRD: Multimodal Deep Fusion of Histology and Spatial Transcriptomics for Cancer Region DetectionTechnical
Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed LearningTechnical
SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding CapabilityTechnical
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel PruningTechnical
Sparse Additive Model Pruning for Order-Based Causal Structure LearningTechnical
Sparse Attention Across Multiple-Context KV CacheTechnical
Sparse Poisson Gamma Belief Networks for High-Dimensional Sparse Count DataTechnical
Sparse Tuning Enhances Plasticity in PTM-based Continual LearningTechnical
Sparse-Scale Transformer with Bidirectional Awareness for Time Series ForecastingTechnical
Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache EvictionTechnical
Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion TransformersTechnical
Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB ViewsTechnical
Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene ReconstructionTechnical
SparseCoop: Cooperative Perception with Kinematic-Grounded QueriesTechnical
SparseRM: A Lightweight Preference Modeling with Sparse AutoencoderTechnical
SparseSurf: Sparse-View 3D Gaussian Splatting for Surface ReconstructionTechnical
SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic QueriesTechnical
Spatial Branch-and-Bound for Computing Multiplayer Nash EquilibriumTechnical
Spatial Graph Attention Network Modeling for Neighborhood-Scale Lead Contamination Risk Prediction Using Publicly Available DataTechnical
Spatial-Frequency Spiking Neural Network for Underwater Object DetectionTechnical
Spatial-Spectral Homogeneous Attacks on Physical-World Large Vision-Language ModelsTechnical
Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic ImputationTechnical
SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic ManipulationTechnical
SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal ReasoningTechnical
Spatially Grouped Curriculum Learning for Multi-Agent Path FindingTechnical
Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract)Technical
Spatio-Temporal Context Learning with Temporal Difference Convolution for Moving Infrared Small Target DetectionTechnical
Spatio-Temporal Distortion Aware Omnidirectional Video Super-ResolutionTechnical
Spatio-Temporal Hierarchical Causal ModelsTechnical
SpatioTemporal Difference Network for Video Depth Super-ResolutionTechnical
Spatiotemporal Transformers with Multiple Instance Learning for Label-Efficient Behavioral Analysis in Autism (Student Abstract)Technical
Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion PredictionTechnical
Speaker Anonymization for ChildrenTechnical
SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language ModelsTechnical
SpecDetect: Simple, Fast, and Training-Free Detection of LLM-Generated Text via Spectral AnalysisTechnical
SpecDiff: Accelerating Diffusion Model Inference with Self-SpeculationTechnical
SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs QuantizationTechnical
Specification-Guided Reinforcement LearningTechnical
Spectral Basis Learning for Expressive Graph Neural Networks in Link PredictionTechnical
Spectral Property-Driven Data Augmentation for Hyperspectral Single-Source Domain GeneralizationTechnical
Spectrally Adaptive Channel-aware Unrolling Network for Compressed SensingTechnical
Speech Recognition Model Improves Text-to-Speech Synthesis Using Fine-Grained RewardTechnical
Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech RecognitionTechnical
SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent RepresentationTechnical
Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored RepresentationsTechnical
SpiderGen: Towards Procedure Generation for Carbon Life Cycle Assessments with Generative AITechnical
SpikCommander: A High-performance Spiking Transformer with Multi-view Learning for Efficient Speech Command RecognitionTechnical
Spike Imaging Velocimetry: Dense Motion Estimation of Fluids Using Spike StreamsTechnical
Spike Stream Memory Transfer for Dynamic Scene ReconstructionTechnical
Spiking Heterogeneous Graph Attention NetworksTechnical
Spiking-Aided Neural Architecture for Efficient and Robust WiFi SensingTechnical
SpikingIR: A Novel Converted Spiking Neural Network for Efficient Image RestorationTechnical
Spikingformer: A Key Foundation Model for Spiking Neural NetworksTechnical
Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map ReconstructionTechnical
SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene CompletionTechnical
Splats in Splats: Robust and Effective 3D Steganography Towards Gaussian SplattingTechnical
Split-Layer: Enhancing Implicit Neural Representation by Maximizing the Dimensionality of Feature SpaceTechnical
Spontaneous Yet Predictable: Shapelet-Driven, Channel-Aware Intention Decoding from Multi-Region ECoGTechnical
Stability-Aware Reinforcement Learning for Robust Class Integration Test Order GenerationTechnical
Stabilizing Cross-Modal Bidirectional Attribution: Few-Shot Adversarial Prompt Tuning for Robust Vision-Language ModelsTechnical
Stabilizing Policy Gradient Methods via Reward ProfilingTechnical
Stabilizing Self-Consuming Diffusion Models with Latent Space FilteringTechnical
Stabilizing Spiking Neurons Through Biologically Inspired PolarizationTechnical
Stable Voting and the Splitting of CyclesTechnical
Stable and Adaptive Fusion for Multi-domain Multi-task RecommendationTechnical
Stage-Aware Graph Contrastive Learning with Node-oriented Mixture of ExpertsTechnical
Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual GroundingTechnical
State Mamba: Spatiotemporal EEG State-Space Model with Dynamic Brain Alignment for Cross-Subject RepresentationTechnical
State Proficiency-Based Adaptive Fine-Tuning for Offline-to-Online Reinforcement LearningTechnical
State-Derivative-Aware Neural Controlled Differential Equations for Multivariate Time Series Anomaly Detection and DiagnosisTechnical
State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal ModelsTechnical
Stationary and Clustering Transformer Hashing for Cross-modal RetrievalTechnical
Statistical Learning Theory for Distributional ClassificationTechnical
Statistically Robust Sparse High-order Interaction ModelTechnical
SteerMusic: Enhanced Musical Consistency for Zero-shot Text-Guided and Personalized Music EditingTechnical
Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image CompressionTechnical
Steering Pretrained Drafters During Speculative DecodingTechnical
Steering Representations, Safeguarding Privacy: A Cross-Modal Privacy Protection Method for Generative AITechnical
Steering Sparse Autoencoder Latents to Control Dynamic Head Pruning in Vision Transformers (Student Abstract)Technical
Steering Visuomotor Policy in Open Worlds via Cross-View Goal AlignmentTechnical
StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain AnalysisTechnical
Step Back to Leap Forward: Self-Backtracking for Symbolic Reasoning and Planning in Language ModelsTechnical
Step-GRPO: Enhancing Reasoning Quality and Efficiency via Structured PRM-Based Reinforcement LearningTechnical
Step-by-step Layered Design GenerationTechnical
StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs Through Knowledge-Reasoning FusionTechnical
Stepwise Contrastive Reasoning for Retrieval-Augmented Generation over Knowledge GraphsTechnical
Steve: Your Personal AI Career CoachTechnical
Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying NetworksTechnical
Stochastic Universal Adversarial Perturbations with Fixed Optimization Constraint and Ensured High-probability TransferabilityTechnical
Stop Mixing Things Up! BISCUIT Teaches Vision-Language Models to Learn New Concepts from Images on the SpotTechnical
StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language ModelsTechnical
Strategic Reasoning over Golog Programs in the Nondeterministic Situation CalculusTechnical
Strategic Tool Enhanced AI Agent for Multi-Issue Negotiation (Student Abstract)Technical
Stratified Knowledge-Density Super-Network for Scalable Vision TransformersTechnical
Stratos: An End-to-End Distillation Pipeline for Customized LLMs Under Distributed Cloud EnvironmentsTechnical
StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and CompressionTechnical
StreamSTGS: Streaming Spatial and Temporal Gaussian Grids for Real-Time Free-Viewpoint VideoTechnical
Streaming Generated Gaussian Process Experts for Online Learning and ControlTechnical
Streaming Generation of Co-Speech Gestures via Accelerated Rolling DiffusionTechnical
StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion ModelTechnical
Strip R-CNN: Large Strip Convolution for Remote Sensing Object DetectionTechnical
StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence DiffusionTechnical
Structural Approach to Guiding a Present-Biased AgentTechnical
Structural Entropy Guided Incremental Learning for Open-World Multimodal Social Event DetectionTechnical
Structure Detection for Contextual Reinforcement LearningTechnical
Structure-Aware Encodings of Argumentation Properties for Clique-widthTechnical
Structure-Enhanced Adapter for Self-Supervised Heterogeneous Graph LearningTechnical
Structure-based RNA Design by Step-wise Optimization of Latent Diffusion ModelTechnical
Structures Meet Semantics: Multimodal Fusion via Graph Contrastive LearningTechnical
Studying Classifier(-Free) Guidance from a Classifier-Centric PerspectiveTechnical
Style-First Authorship Verification for Academic Integrity in the Generative AI Era (Student Abstract)Technical
Style4D-Bench: A Benchmark Suite for 4D StylizationTechnical
StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio JailbreakTechnical
StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous DrivingTechnical
StyleFM: Frequency Manipulation Empowered by Recursive Attention on Diffusion Models for Arbitrary Style TransferTechnical
StyleProto: Style-Augmented Prototype Learning for Cross-Domain Few-Shot Object DetectionTechnical
StyleSentinel: Reliable Artistic Copyright Verification via Stylistic FingerprintsTechnical
StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative FeedbackTechnical
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert MergingTechnical
SubGCache: Accelerating Graph-based RAG with Subgraph-level KV CacheTechnical
Subgraph Encoding with Bicentric Sphere Node Labeling and Pooling for Link PredictionTechnical
Subspace-Aware Graph Construction and Contrastive Alignment for Multimodal Recommendation with Large Language ModelsTechnical
Suit the Remedy to the Retriever: Interpretable Query Optimization with Retriever Preference Alignment for Vision-Language RetrievalTechnical
Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training (Abstract Reprint)Technical
Superior Runtime Guarantees for the MOEA/D Multi-Objective Optimizer via Weighted-Sum DecompositionTechnical
Supervised Dynamic Dimension Reduction with Deep Neural NetworkTechnical
SurgPub-Video: A Comprehensive Surgical Video Framework for Enhanced Surgical Intelligence in Vision-Language ModelTechnical
Surgical AI Copilot: Energy-Based Fourier Gradient Low-Rank Adaptation for Surgical LLM Agent Reasoning and PlanningTechnical
Surrogate as Teacher: Distillation-Guided Graph Poisoning AttackTechnical
SwiftVideo: A Unified Framework for Few-Step Video Generation Through Trajectory-Distribution AlignmentTechnical
Syllogism-Inspired TableQA: Evidentialization Makes Decomposition Reasoning and Answer Verification More ReliableTechnical
SymGS: Leveraging Reflective Symmetries for 3DGS CompressionTechnical
Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned AgentsTechnical
Symbolic Task Inference in Deep Reinforcement Learning (Abstract Reprint)Technical
Symmetric Aggregation of Conformity Scores for Efficient Uncertainty SetsTechnical
Symmetrical Flow Matching: Unified Image Generation, Segmentation, and Classification with Score-Based Generative ModelsTechnical
Symmetries and Other Variations of “End-Recursive” HTN Problems: Mapping the Border Between Decidable and Undecidable RestrictionsTechnical
Symmetry Breaking for Inductive Logic ProgrammingTechnical
Symmetry-Aware Transformer Training for Automated PlanningTechnical
Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-ExpertsTechnical
SynWeather: Weather Observation Data Synthesis Across Multiple Regions and Variables via a General Diffusion TransformerTechnical
SyncBrain: Exploring Brain Functional Dynamics Through Neural Oscillatory SynchronizationTechnical
SynerDetect: Hierarchical Synergistic Learning for Generalizable AI-Generated Image DetectionTechnical
Synergizing Multigrid Algorithms with Vision Transformer: A Novel Approach to Enhance the Seismic Foundation ModelTechnical
Synthetic Forgetting Without Access: A Few-Shot Zero-Glance Framework for Machine UnlearningTechnical
Synthetic-to-Real Transfer Learning for League of Legends Minimap Object Detection (Student Abstract)Technical
System L: Toward System 2-Style Legal ReasoningTechnical
S²Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual ScreeningTechnical
S²Flow: Towards Fast and Authentic Training-Free High-Resolution Video GenerationTechnical
S²HyRec: Self-Supervised Hypergraph Sequential RecommendationTechnical
S²Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object DetectionTechnical
S³-MSD: Large Vision-Language Model for Explainable and Generalizable Multi-modal Sarcasm DetectionTechnical
S³: Spiking Neurons as an Isolating Segmenter for Brain Signal DecodingTechnical
T-APT: Text-Guided Modality-Aware Prompt Tuning for Arbitrary Multimodal Remote Sensing Data Joint ClassificationTechnical
T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low BitratesTechnical
T-LoRA: Single Image Diffusion Model Customization Without OverfittingTechnical
T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual GraphsTechnical
T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object DetectionTechnical
T-SKM-Net: Trainable Neural Network Framework for Linear Constraint Satisfaction via Sampling Kaczmarz-Motzkin MethodTechnical
T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree SearchTechnical
T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image ModelTechnical
T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual FusionTechnical
T3former: Temporal Graph Classification with Topological Machine LearningTechnical
T4NMTD: Transition-Centric Reinforcement Learning for Non-Markovian Task DecompositionTechnical
TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy OptimizationTechnical
TARA: Token-Aware LoRA for Composable Personalization in Diffusion ModelsTechnical
TASE: Token Awareness and Structured Evaluation for Multilingual Language ModelsTechnical
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph ConstructionTechnical
TCoT: Trajectory Chain-of-Thoughts for Robotic Manipulation with Failure Recovery in Vision-Language-Action ModelTechnical
TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex ModelingTechnical
TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual PredictionTechnical
TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT AlignmentTechnical
TFD-Net: Towards Intelligent Time-Frequency Mode Decomposition with Practical ApplicationsTechnical
TFRank: Think-Free Reasoning Enables Practical Pointwise LLM RankingTechnical
TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic ReconstructionTechnical
TGCA-LLM: Time-Aware Graph-Text Contrastive Alignment for Enhancing LLMs in Temporal Knowledge Graph CompletionTechnical
TGCD: A Framework for Generalized Category Discovery in Time-Series DataTechnical
TGDD: Trajectory Guided Dataset Distillation with Balanced DistributionTechnical
THGB: A Comprehensive Benchmark for Text-attributed Heterogeneous GraphsTechnical
TIDE: Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image GenerationTechnical
TIM++: Transductive Information Maximization for Few-Shot CLIPTechnical
TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization AbilityTechnical
TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMsTechnical
TIV: Thought Injection via Vectors for Efficient Reasoning in Large Reasoning ModelsTechnical
TLAGC: Taylor Linear Attention-Guided Graph Convolutions for Revealing Spatial Domains in Spatial Multi-Omics DataTechnical
TMAE:Learning Targeted Multi-Agent Exploration via Causal InferenceTechnical
TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy ModalitiesTechnical
TO-GATE: Clarifying Questions and Summarizing Responses with Trajectory Optimization for Eliciting Human PreferenceTechnical
TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language ModelsTechnical
TOP-RL: Task-Optimized Progressive Token Pruning with Reinforcement Learning for Vision Language ModelsTechnical
TOPOGRAPH: Topology-Preserving Graph Reduction with Adaptive Structure for Persistent HomologyTechnical
TORA: Train Once, Realign Anytime for Offline Multi-Objective Reinforcement LearningTechnical
TOSC: Task-Oriented Shape Completion for Open-World Dexterous Grasp Generation from Partial Point CloudsTechnical
TPR: A Training Procedure Representation to Augment XR Simulations with LLMsTechnical
TR-DQ: Time-Rotation Diffusion QuantizationTechnical
TRACE: A Generalizable Drift Detector for Streaming Data-Driven OptimizationTechnical
TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate DetectionTechnical
TRACE: Trajectory-based Activation Change Estimation for Task-specific Data SelectionTechnical
TRACE: Transformation-Aware Graph Refinement for Reaction Condition PredictionTechnical
TRIPLE: Theory-Driven Integration of Planned and Habitual Behaviors for LLM-based PersonalizationTechnical
TRT: Harnessing Tensor Ring Transformer for Hyperspectral Image Super-ResolutionTechnical
TRUST: Leveraging Text Robustness for Unsupervised Domain AdaptationTechnical
TRUST: Transaction Risk via Unified Sequence and TopologyTechnical
TSBOW – Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather ConditionsTechnical
TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph PerspectiveTechnical
TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian SplattingTechnical
TSPO: Temporal Sampling Policy Optimization for Long-form Video Language UnderstandingTechnical
TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio ModelsTechnical
TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action ModelsTechnical
TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in DouyinTechnical
TTVAE: Transformer-Based Generative Modeling for Tabular Data Generation (Abstract Reprint)Technical
TVChain: Leveraging Textual-Visual Prompt Chains for Jailbreaking Large Vision-Language ModelsTechnical
TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement LearningTechnical
TWINFUZZ: Dual-Model Fuzzing for Robustness Generalization in Deep LearningTechnical
TWiST: Temporal Weakly-Supervised Triplets Recognition in Surgical Videos (Student Abstract)Technical
TaREx: Reinforcement Learning for Code-Driven Table ReasoningTechnical
Tab-PET: Graph-Based Positional Encodings for Tabular TransformersTechnical
TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token FocusingTechnical
TabGeoFlow: A Geometric Flow Matching Model for Tabular Data SynthesisTechnical
Tabular Learnwares Can Be Repurposed for Seemingly Irrelevant New TasksTechnical
Tackling Dual-stage Missing Modalities in Brain Tumor Segmentation via Robust Modality Reconstruction and Prompt-guided Modality AdaptationTechnical
Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse PackTechnical
TacpAgent: Enhancing Student Engagement in Classroom Exercises Through LLM-Generated FeedbackTechnical
TactGen: Tactile Sensory Data Generation via Zero-Shot Sim-to-Real Transfer (Abstract Reprint)Technical
Tailored ViT Slimming: Budget-Aware Multi-Dimensional Sparsity Regularization for Vision Transformers Pruning (Student Abstract)Technical
Talk, Snap, Complain: Validation-Aware Multimodal Expert Framework for Fine-Grained Customer GrievancesTechnical
Talk2Code: A Multi-Turn Interaction Benchmark with Dual-Track Evaluation for Code GenerationTechnical
Talk2Image: A Multi-Agent System for Multi-Turn Image Generation and EditingTechnical
Talking Trails: LLM-Enhanced Spatiotemporal Trajectory Modeling for E-Bike Delivery Route PlanningTechnical
Talon: Breaking the Synchronization Barrier in Speculative Decoding with Hybrid Model-based and Retrieve-based DraftingTechnical
Taming Cascaded Mixture-of-Experts for Modality-missing Multi-modal Salient Object DetectionTechnical
Taming the Phantom: Token-Asymmetric Filtering for Hallucination Mitigation in Large Vision-Language ModelsTechnical
Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic EnvironmentsTechnical
TarPro: Targeted Protection Against Malicious Image EditingTechnical
Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability PerspectiveTechnical
Target-Balanced Score DistillationTechnical
TargetVAU: Multimodal Anomaly-Aware Reasoning for Target Behavior Understanding in VideosTechnical
Targeted Data Protection for Diffusion Model by Matching Training TrajectoryTechnical
Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and ExplanationTechnical
Targeting Borderline Fraudsters: Multi-View Hypergraph Fraud Detection with LLM-Guided Contrastive LearningTechnical
Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM AlignmentTechnical
Targeting in Multi-Criteria Decision MakingTechnical
Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated DataTechnical
Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric RefinementTechnical
Task-Aware Meta-Learning on Heterogeneous Knowledge Graph for POI RecommendationTechnical
Task-Aware Retrieval Augmentation for Dynamic RecommendationTechnical
Task-Specific Distance Correlation Matching for Few-Shot Action RecognitionTechnical
TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models TrainingTechnical
TaxReasoning: Benchmarking Knowledge-Intensive Mathematical Reasoning with Evolving Tax LawsTechnical
Teach AI What It Doesn’t KnowTechnical
Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement LearningTechnical
TechCoach: Towards Technical-Point-Aware Descriptive Action CoachingTechnical
Tell as You Want: Customizing Image Narrative with Knowledge and ThoughtsTechnical
Template-Theorems Graph Construction to Enhance Mathematical Reasoning Capabilities of LLMTechnical
Temporal Calibrating and Distilling for Scene-Text Aware Text-Video RetrievalTechnical
Temporal Dynamics Enhancer for Directly Trained Spiking Object DetectorsTechnical
Temporal Inconsistency Guidance for Super-resolution Video Quality AssessmentTechnical
Temporal Object-Aware Vision Transformer for Few-Shot Video Object DetectionTechnical
Temporal Properties of Conditional Independence in Dynamic Bayesian NetworksTechnical
Temporal and Spatial Representation Learning for Multimodal Low-Beam 3D Object DetectionTechnical
Temporal-Consistent Video Restoration with Pre-trained Diffusion ModelsTechnical
Tensor Decomposition and Language Description for Open-Vocabulary Object DetectionTechnical
Tensorized Label Learning via Balanced Tensor RegressionTechnical
TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial DomainsTechnical
Test-Time Preference Optimization for Image RestorationTechnical
Test-Time Reinforcement Learning for GUI Grounding via Region ConsistencyTechnical
Test-driven Reinforcement Learning in Continuous ControlTechnical
Test-time Diverse Reasoning by Riemannian Activation SteeringTechnical
Test-time Prompt InterventionTechnical
Testing Under Strategic Manipulation: Mechanism Design for Human and AI InstitutionsTechnical
Text-Guided Channel Perturbation and Pre-Trained Knowledge Integration for Unified Multi-Modality Image FusionTechnical
Text-Guided Gradient Refinement: Resolving Multimodal Gradient Conflicts to Boost Adversarial Attacks on Vision-Language ModelsTechnical
Text-based Aerial-Ground Person RetrievalTechnical
Text-guided Controllable Diffusion for Realistic Camouflage Images GenerationTechnical
Text-to-Scene with Large Reasoning ModelsTechnical
TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text RenderingTechnical
TextShield-R1: Reinforced Reasoning for Tampered Text DetectionTechnical
Textual Self-Attention Network: Test-Time Preference Optimization Through Textual Gradient-Based AttentionTechnical
Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry NetworkTechnical
The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive CurationTechnical
The Avengers: A Routing Recipe for Collective Intelligence in Language ModelsTechnical
The Confidence Trap: Gender Bias and Predictive Certainty in LLMsTechnical
The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order LogicTechnical
The Cost and Complexity of Minimizing Envy in House Allocations (Abstract Reprint)Technical
The Curious Case of Analogies: Investigating Analogical Reasoning in Large Language ModelsTechnical
The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans?Technical
The Essentials of AI for Life and Society: A Full-Scale AI Literacy Course Accessible to AllTechnical
The Finer the Better: Towards Granular-aware Open-set Domain GeneralizationTechnical
The Fixed-Point of Distrust: A Formal Theory of Perceived Systemic IncompetenceTechnical
The Future Is Neuro-Symbolic: Where Has It Been, and Where Is It Going?Technical
The GATTACA Framework: Graph Neural Network-Based Reinforcement Learning for Controlling Biological NetworksTechnical
The Illusion of Fairness: Auditing Fairness Interventions in Algorithmic Hiring with Audit StudiesTechnical
The Last Byte: Learning Just Enough for Machine-Oriented Image CompressionTechnical
The Limitations and Power of NP-Oracle Based Functional Synthesis TechniquesTechnical
The Other Mind: How Language Models Exhibit Human Temporal CognitionTechnical
The Power of Initial Investigation in Audit GamesTechnical
The Publication Choice ProblemTechnical
The River Voting MethodTechnical
The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint)Technical
The Semantic Architect: How FEAML Bridges Structured Data and LLMs for Multi-Label TasksTechnical
The Shepherd Test: How Will Super Intelligent Agents Balance Care and Control in Asymmetric Relationships?Technical
The Silent Amplifier: In-Context Examples Fuel Bias in Large Language ModelsTechnical
The Strong Lottery Ticket Hypothesis for Multi-Head Attention MechanismsTechnical
The Structure-Equivalent Prior: Unifying Temporal Dynamics and 3D Evolution in 4D Latent SpaceTechnical
The Tatort Test of Intelligence: Towards Narrative Comprehension as a Benchmark for AITechnical
The Visual Prism: Refracting Images into Parallel Multilingual Descriptions with Structured Visual GuidanceTechnical
Themis: Automated Constraint-Aware Test Synthesis Framework for Code Reinforcement LearningTechnical
Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport (Abstract Reprint)Technical
Theoretical and Empirical Analysis of Lehmer Codes to Search Permutation Spaces with Evolutionary AlgorithmsTechnical
Theory-of-Mind in Partially Observed, Mixed-Motive GamesTechnical
Thermal-Physics Guided Infrared Image Super-Resolution with Dynamic High-Frequency AmplificationTechnical
Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual SegmentationTechnical
Think How Your Teammates Think: Active Inference Can Benefit Decentralized ExecutionTechnical
Think Then Rewrite: Reasoning Enhanced Query Rewriting for Domain Specific RetrievalTechnical
Think Wise, Collaborate Effectively: A Rationale-Aware LLM-Based Recommender with Reinforcement Learning from Collaborative SignalsTechnical
Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-MakingTechnical
Think-J: Learning to Think for Generative LLM-as-a-JudgeTechnical
Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn InteractionTechnical
Thinking Aesthetics Assessment of Image Color Temperature: Models, Datasets and BenchmarksTechnical
Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented ReasoningTechnical
Thinking Through the Hands: An Exploratory Study of Hand Movements to Assess Students Problem-Solving in Mechanistic Reasoning TasksTechnical
Through the Water: Refractive Gaussian Splatting for Water Surface ScenesTechnical
TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion RecognitionTechnical
Tight Robustness Certification Through the Convex Hull of ℓ₀ AttacksTechnical
Tighter Truncated Rectangular Prism Approximation for RNN Robustness VerificationTechnical
TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual AnalysisTechnical
Time Series Class-Incremental Learning via Confidence-guided Mask Distillation and Prototype-guided Contrastive LearningTechnical
Time Series Forecasting via Direct Per-Step Probability Distribution ModelingTechnical
Time Shuffle: A Transferability-Booster for Multiple Audio Adversarial TasksTechnical
Time-Frequency Augmented Multi-level Contrastive Clustering for Time SeriesTechnical
Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning ModelTechnical
Time-Series Anomaly Detection with Graph-Based Self-Supervised Learning and Foundation Models: Towards Real-World ApplicationsTechnical
Time2Agri: Temporal Pretext Tasks for Agricultural MonitoringTechnical
TimeBill: Time-Budgeted Inference for Large Language ModelsTechnical
TimeCAP: A Channel-Aware Pre-Training Framework for Multivariate Time Series ForecastingTechnical
TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise DecodingTechnical
Timestep-Compressed Attack on Spiking Neural Networks Through Timestep-Level BackpropagationTechnical
TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction TasksTechnical
To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal PerformanceTechnical
ToC: Tree-of-Claims Search with Multi-Agent Language ModelsTechnical
Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive ModelsTechnical
Token-Context Attention for NLI: An Alternative to Self-AttentionTechnical
TokenPowerBench: Benchmarking the Power Consumption of LLM InferenceTechnical
Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based RecommendationTechnical
TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI AgentsTechnical
Too Sure for Our Own Good: A User Study on AI Confidence and Human RelianceTechnical
ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool learningTechnical
ToolSmith: A Multi-Agent Framework for Enterprise Tool CreationTechnical
Top-Down Semantic Refinement for Image CaptioningTechnical
Topo-GraT: Learning to Grow with Causal Graph Transformers (Student Abstract)Technical
Topological Federated Clustering via Gravitational Potential Fields Under Local Differential PrivacyTechnical
Topology-Aware Vision Transformers for Enhanced Scene RecognitionTechnical
Topology-Enhanced and Label Correlation-Aware Model for Protein-Protein Interaction PredictionTechnical
Topology-Inspired Backward-Free Framework for Test-Time Adaptation in Medical DetectionTechnical
Topology-aware Knowledge Preservation for Class-Incremental LearningTechnical
TouchFormer: A Robust Transformer-based Framework for Multimodal Material PerceptionTechnical
Toward Artificial MetacognitionTechnical
Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention GuidanceTechnical
Toward Causal Foundation World Models: From Representation to Decision-MakingTechnical
Toward Controllable and Trustworthy LLM Reasoning: From Failure Mapping to Cognition-inspired Control and Real-world ImpactTechnical
Toward Gaze Target Detection of Young Autistic ChildrenTechnical
Toward Multimodal Fake News Detection by Multi-perspective Rationale Generation and VerificationTechnical
Toward Real-World High-Precision Image Matting and SegmentationTechnical
Toward Simulating Networked Societies with Formal Institutions Using AI AgentsTechnical
Toward Time-Continuous Data Inference in Sparse Urban CrowdSensingTechnical
Toward Trustworthy AI for Decision Making in Population HealthTechnical
Toward the Frontiers of Reliable Diffusion Sampling via Adversarial Sinkhorn Attention GuidanceTechnical
Towards 3D Object-Centric Feature Learning for Semantic Scene CompletionTechnical
Towards Accurate 3D Object Detection in Adverse Weather by Leveraging 4D Radar for LiDAR Geometry EnhancementTechnical
Towards Acyclic Preference Evaluation of Language Models via Multiple EvaluatorsTechnical
Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-TuningTechnical
Towards Affordance-Aware Robotic Dexterous Grasping with Human-like PriorsTechnical
Towards Agents That Exhibit Human-Like Autonomy in Complex EnvironmentsTechnical
Towards Aligned and Efficient Large Language ModelsTechnical
Towards Authentic Movie Dubbing with Retrieve-Augmented Director-Actor Interaction LearningTechnical
Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection (Abstract Reprint)Technical
Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic MethodologyTechnical
Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language ModelsTechnical
Towards Better Code Understanding in Decoder-Only Models with Contrastive LearningTechnical
Towards Better Correctness and Efficiency in Code GenerationTechnical
Towards Better IncomLDL: We Are Unaware of Hidden Labels in AdvanceTechnical
Towards Capable and Secure Autonomous Computer-Use Agents (Student Abstract)Technical
Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen ScenariosTechnical
Towards Continually-Evolving AI: Selective and Expandable Multimodal Memory SystemTechnical
Towards Data-Efficient Deep Learning for RNA 3D Structure Prediction and DesignTechnical
Towards Distance-Invariant Radio Frequency Fingerprinting via Augmented Unsupervised LearningTechnical
Towards Effective Code-Integrated ReasoningTechnical
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF BenchmarkTechnical
Towards Effective and Efficient Context-aware Nucleus Detection in Histopathology Whole Slide ImagesTechnical
Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation ModelsTechnical
Towards Efficient Low-rate Image Compression with Frequency-aware Diffusion Prior RefinementTechnical
Towards Efficient and Effective Interactive 3D SegmentationTechnical
Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action ModelingTechnical
Towards Explainable Video Camouflaged Object Detection: SAM2 with Eventstream-Inspired DataTechnical
Towards Fairness in Transportation Gig Markets: Identifying, Imitating, and Mitigating Algorithm Discrimination via Deep Reinforcement LearningTechnical
Towards Federated Clustering: A Client-wise Private Graph Aggregation FrameworkTechnical
Towards Generalist Robot Learning from Internet Video: A Survey (Abstract Reprint)Technical
Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse ObservationsTechnical
Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware DiffusionTechnical
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial DefectsTechnical
Towards Human-centered Proactive Conversational AITechnical
Towards Illumination-Aware Restoration of Metalens-Captured Images: A New Dataset and a Strong BaselineTechnical
Towards Inclusive AI: Advancing Multilingual Large Language ModelsTechnical
Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic SpaceTechnical
Towards Long-window Anchoring in Vision-Language Model DistillationTechnical
Towards Multimodal Continual Knowledge Embedding with Modality Forgetting ModulationTechnical
Towards Multiple Missing Values-resistant Unsupervised Graph Anomaly DetectionTechnical
Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency DifferencingTechnical
Towards Nonlinear Sparse AUC Maximization via Compositional Stochastic Hard ThresholdingTechnical
Towards OOD Generalization in Dynamic Graphs via Causal Invariant LearningTechnical
Towards Offline Imitation Learning: Strictly Batch Settings, Generalization, and Variability in ExpertiseTechnical
Towards Privacy-Protected Generalized Gaze Estimation Using Diffusion Models and Domain Stability Adaptation FrameworkTechnical
Towards Provably Secure and Highly Robust Generative Image Steganography Leveraging Latent Diffusion ModelTechnical
Towards Provably Unlearnable Examples via Bayes Error OptimizationTechnical
Towards Real-Time Neutral Atom Array Assembly via Unsupervised Hologram Generation and Path OptimizationTechnical
Towards Reinforcement Learning from Neural Feedback: Mapping fNIRS Signals to Agent PerformanceTechnical
Towards Robust Edge Model Adaptation via Elastic Architecture SearchTechnical
Towards Robust Event-Based Depth Estimation: Bridging Synthetic and Real Domains with Motion AdaptationTechnical
Towards Robust Human–AI Decision-Making via Learning-to-DeferTechnical
Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and DefenseTechnical
Towards Robust and Interpretable Event–Frame Fusion for Autonomous DrivingTechnical
Towards Robust, Reliable, and Generalized Medical AITechnical
Towards Scalable Web Accessibility Audit with MLLMs as CopilotsTechnical
Towards Single Exponential Time for Temporal and Spatial Reasoning: A Study via Redundancy and Dynamic ProgrammingTechnical
Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion ModelsTechnical
Towards Synthesizing High-Dimensional Tabular Data with Limited SamplesTechnical
Towards Temporal Fusion Beyond the Field of View for Camera-based Semantic Scene CompletionTechnical
Towards Test-time Efficient Visual Place Recognition via Asymmetric Query ProcessingTechnical
Towards Training-Free and Accurate ANN-to-SNN Conversion via Activation-Aware RedistributionTechnical
Towards Trustworthy Multimodal AI SystemsTechnical
Towards Ultrasound-based Reliable Disease Diagnosis Using Causal InferenceTechnical
Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNsTechnical
Towards Understanding In-Context Learning of Transformers Under Non-I.I.D. ScenariosTechnical
Towards Unified Vision-Language Models with Incomplete Multi-Modal InputsTechnical
Towards Zero-Shot Diabetic Retinopathy Grading: Learning Generalized Knowledge via Prompt-Driven Matching and EmulatingTechnical
Towards a Common Framework for AutoformalizationTechnical
Towards a Rigorous Understanding of the Population Dynamics of the NSGA-III: Tight Runtime BoundsTechnical
Towards an Ontology-Driven Approach to Document Bias (Abstract Reprint)Technical
TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as AgentsTechnical
TraceTrans: Translation and Spatial Tracing for Surgical PredictionTechnical
Tracing the Heart’s Pathways: ECG Representation Learning from a Cardiac Conduction PerspectiveTechnical
TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track ConstraintsTechnical
Tracking and Segmenting Anything in Any ModalityTechnical
Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured VideosTechnical
Tractable Sharpness-Aware Learning of Probabilistic CircuitsTechnical
Tractable Weighted First-Order Model Counting with Bounded Treewidth Binary EvidenceTechnical
Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational CapabilitiesTechnical
Traffic Signal Plans Explorer: A General Framework for Visualising Traffic EvolutionTechnical
Trainable EEG Interpolation and Structure-Sharing Dual-Path Encoders for Brain-Assisted Target Speaker ExtractionTechnical
Training and Inference Within 1 Second – Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature TailoringTechnical
Training-Free ANN-to-SNN Conversion for High-Performance Spiking TransformersTechnical
Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward FeedbackTechnical
Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object MemoryTechnical
Training-free Boosting for Few-shot Segmentation via Generalizing Semantic MiningTechnical
TrajAgg: Dual-Scale Feature Aggregation with Hybrid Training for Trajectory Similarity Computation in Free SpaceTechnical
TrajEvo: Trajectory Prediction Heuristics Design via LLM-driven EvolutionTechnical
TransFR: Transferable Federated Recommendation with Adapter Tuning on Pre-trained Language ModelsTechnical
TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language ModelTechnical
Transferability of Adversarial Attacks in Video-based MLLMs: A Cross-modal Image-to-Video ApproachTechnical
Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial PerturbationTechnical
Transferable Graph Condensation from the Causal PerspectiveTechnical
Transferable Hypergraph Attack via Injecting Nodes into Pivotal HyperedgesTechnical
Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong GeneralizationTechnical
Transferable RL for Real-World Navigation Using Semantic Segmentation and Bird’s-Eye View AbstractionTechnical
Transferring Causal Driving Patterns for Generalizable Traffic Simulation with Diffusion-Based DistillationTechnical
Transform-Free Feature Coding via Entropy-Constrained Vector QuantizationTechnical
Transformer with Controlled Attention for Synchronous Motion CaptioningTechnical
Transformers in Pseudo-Random Number Generation: A Dual Perspective on Theory and PracticeTechnical
Transolver Is a Linear Transformer: Revisiting Physics-Attention Through the Lens of Linear AttentionTechnical
Transparent Networks for Multivariate Time SeriesTechnical
Trauma THOMPSON: A Dataset and Realistic Generative Framework for AI Copilots in Emergency CareTechnical
TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured ReasoningTechnical
Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment StrategiesTechnical
Tree-Based Stochastic Optimization for Solving Large-Scale Urban Network Security GamesTechnical
TreeBridge: Aligning LLM Embeddings in Industrial Recommender SystemsTechnical
TriFusion-IDS: A Multimodal Graph-Tabular-Text Contrastive Framework for Cross-Dataset Intrusion DetectionTechnical
Trimming the Fat: Redundancy-Aware Acceleration Framework for DGNNsTechnical
TrinityDNA: A Bio-Inspired Foundational Model for Efficient Long-Sequence DNA ModelingTechnical
TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text EditingTechnical
Truncated Counterfactual Learning for Anytime Multi-Agent Path FindingTechnical
TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage PredictionTechnical
Trusted Multi-view Learning for Long-tailed ClassificationTechnical
Trustworthy AI-Assisted Programming: Detection and Repair of Unreliable CodeTechnical
Trustworthy Autonomy Without Human Intervention in Uncertain DomainsTechnical
Trustworthy Classification for Complex Social Surveys: A Memory-Enhanced Hierarchical Framework with Calibrated UncertaintyTechnical
Truth, Justice, and Secrecy: Cake Cutting Under Privacy ConstraintsTechnical
Truth-Tracking Evaluation in Opinion-Based ArgumentationTechnical
TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge GraphsTechnical
TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video GroundingTechnical
TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-TuningTechnical
Tuning Medical Foundation Models for Inner Ear Temporal CT Analysis with Plug-and-play Domain Knowledge AggregatorTechnical
Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks Using Hyperparameter TuningTechnical
Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting ModelsTechnical
TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera TuningTechnical
Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile DevicesTechnical
TweezeEdit: Consistent and Efficient Image Editing with Path RegularizationTechnical
Two Constraint Compilation Methods for Lifted PlanningTechnical
Two Heads Are Better than One: Distilling Large Language Model Features into Small Models with Feature Decomposition and MixtureTechnical
U2B: Scale-unbiased Representation Converter for Graph Classification with Imbalanced and Balanced Scale DistributionsTechnical
U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon TasksTechnical
UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery Using Gaussian SplattingTechnical
UCPO: A Universal Constrained Combinatorial Optimization Method via Preference OptimizationTechnical
UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-JudgeTechnical
UDCH: Unsupervised Dynamic Weighted Cluster-cooperative Hashing for Cross-modal RetreivalTechnical
UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement LearningTechnical
UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text EditingTechnical
UMNet: Uncertainty-guided Memory Network for Hyperspectral PansharpeningTechnical
UNO! UNified Offline Training Paradigm for Learning Path RecommendationTechnical
UNSEEN: Enhancing Dataset Pruning from a Generalization PerspectiveTechnical
UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World ModelTechnical
UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality AssessmentTechnical
UQ-ViT: Harmonizing Extreme Activations with Hardware-Friendly Uniform Quantization in Vision TransformersTechnical
URPO: A Unified Reward & Policy Optimization Framework for Large Language ModelsTechnical
URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document UnderstandingTechnical
USE: A Unified Model for Universal Sound Separation and ExtractionTechnical
USPR: Learning a Unified Solver for Profiled RoutingTechnical
UV-RGS: Relightable 3D Gaussian Splatting from Unposed Views Under Varied IlluminationsTechnical
UVLM: Benchmarking Video Language Model for Underwater World UnderstandingTechnical
UltraGen: High-Resolution Video Generation with Hierarchical AttentionTechnical
Ultralight Polarity-Split Neuromorphic SNN for Event-Stream Super-ResolutionTechnical
Unaligned UAV RGBT Tracking: A Largescale Benchmark and a Novel ApproachTechnical
Unbiased Rectification for Sequential Recommender Systems Under Fake OrdersTechnical
Uncertainty Quantification for Machine Learning: One Size Does Not Fit AllTechnical
Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical ReasoningTechnical
Uncertainty-Guided View-Strength-Aware Feature Utilization for Multi-View ClassificationTechnical
Uncertainty-Propelled Physics-MAE Fusion for Self-Supervised Diffusion-Weighted Image DenoisingTechnical
Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring ApproachTechnical
Uncovering Hidden Degeneration: A Physics-Guided Bidirectional Inference Framework for Industrial Time Series PredictionTechnical
Uncovering Pretraining Code in LLMs: A Syntax-Aware Attribution ApproachTechnical
Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor AttacksTechnical
Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive ForensicsTechnical
Uncovering and Mitigating Transient Blindness in Multimodal Model EditingTechnical
Under-Approximating Semantics in Clustered Assumption-Based ArgumentationTechnical
Understanding Dynamic Scenes in Ego Centric 4D Point CloudsTechnical
Understanding Interaction as You Need: Intention-Driven Pedestrian Behavior PredictionTechnical
Understanding and Enhancing Differentiable Architecture Search from Information Bottleneck PerspectiveTechnical
Understanding the Effects of GenAI as No-Code Alternative for Teaching Machine Learning WorkflowsTechnical
Understanding the Impact of Proportionality in Approval-Based Multiwinner ElectionsTechnical
Understanding the Management of Rape Trauma with AI and NeuroimagingTechnical
UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-LocalizationTechnical
UniAPO: Unified Multimodal Automated Prompt OptimizationTechnical
UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and PerceptionTechnical
UniC-Lift: Unified 3D Instance Segmentation via Contrastive LearningTechnical
UniCUE: Unified Recognition and Generation Framework for Chinese Cued Speech Video-to-Speech GenerationTechnical
UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic AlignmentTechnical
UniHOI: Unified Human-Object Interaction Understanding via Unified Token SpaceTechnical
UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link PredictionTechnical
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding LearningTechnical
UniMGS: Unifying Mesh and 3D Gaussian Splatting with Single-Pass Rasterization and Proxy-Based DeformationTechnical
UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous DrivingTechnical
UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal DataTechnical
UniMo: Unified Motion Generation and Understanding with Chain of ThoughtTechnical
UniScene-MoTion: Unified Scene & Motion-aware Diffusion Transition FrameworkTechnical
UniSketch: A Unified Framework for Parametric Sketch Generation and Constraint PredictionTechnical
UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data (Student Abstract)Technical
Unified Interaction Consistency Learning for Single-Source Domain-Generalized Object Detection in Urban SceneTechnical
Unified Minimax Optimization Framework for Propensity Score Estimation in Debiased RecommendationTechnical
Unified Mixture-of-Experts Framework for Joint Cardiac and Vascular Ultrasound Analysis and Report GenerationTechnical
Unified Representation Causal Prompt Distillation for Re-Inference-Free Lifelong Person Re-IdentificationTechnical
Unified Structural Factors for Transfer Learning Generalization with PAC-Bayesian GuaranteesTechnical
Unified View Extraction with Low-Rankness and Smoothness Fusion for Multi-View Subspace ClusteringTechnical
Unifying Channel Independence and Mixing: Multi-Scale Patch Recursion for Global–Local Representation Synergy in Multivariate Time Series ForecastingTechnical
Unifying Locality of KANs and Feature Drift Compensation Projection for Data-Free Replay Based Continual Face Forgery DetectionTechnical
Unifying Multi-View Knowledge for Graph Learning via Model CollaborationTechnical
Unintended Misalignment from Agentic Fine-Tuning: Risks and MitigationTechnical
Universal Adversarial Purification with DDIM Metric Loss for Stable DiffusionTechnical
Universal Compressed Image Restoration via Codec-Aware Conditioning with Reinforcement LearningTechnical
Universal EEG Epilepsy Detection via Evidential Multi-View De-BiasingTechnical
Universal Learning of Stochastic Dynamics for Exact Belief Propagation Using Bernstein Normalizing FlowsTechnical
Universal Safety Controllers with Learned PropheciesTechnical
Unlearning in Cross-Modal Retrieval via Prior-Prototype Guided Partitioned DampeningTechnical
Unleashing Semantic and Geometric Priors for 3D Scene CompletionTechnical
Unleashing the Potential of Large Language Models for Text-to-Image Generation Through Autoregressive Representation AlignmentTechnical
Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular BarriersTechnical
Unlocking Dynamic Inter-Client Spatial Dependencies: A Federated Spatio-temporal Graph Learning Method for Traffic Flow ForecastingTechnical
Unlocking Efficient Vehicle Dynamics Modeling via Analytic World ModelsTechnical
Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed GraphsTechnical
Unlocking the Power of Large Multimodal Models for Robot Learning: Robustness, Generalization, and OpportunitiesTechnical
Unnoticed Yet Effective: A Hybrid Physical Camouflage Framework Against DNNs and Human PerceptionTechnical
Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized ModelsTechnical
Unplugged Activities on Machine Learning and Their Evaluation Through Mental States AttributionTechnical
Unreal-MAP: Unreal-Engine-Based General Platform for Multi-agent Reinforcement LearningTechnical
Unsupervised Combinatorial Probabilistic Reasoning: Probabilistic Coin Change ProblemTechnical
Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape MatchingTechnical
Unsupervised Feature Selection Through Group DiscoveryTechnical
Unsupervised Motion-Compensated Decomposition for Cardiac MRI Reconstruction via Neural RepresentationTechnical
Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCTTechnical
Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided AlignmentTechnical
Unsupervised Semantic Discovery via Global and Local Semantic Alignment in Multimodal ClusteringTechnical
Unsupervised Single-Channel Audio Separation with Diffusion Source PriorsTechnical
Unveiling AI Safety in Fine-tuning Quantized ModelTechnical
Unveiling the Attribute Misbinding Threat in Identity-Preserving ModelsTechnical
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal OptimizationTechnical
Unveiling the Landscape of Clinical Depression Assessment: From Behavioral Signatures to Psychiatric ReasoningTechnical
Uplift Modeling with Delayed Feedback: Identifiability and AlgorithmsTechnical
Urban Incident Prediction with Graph Neural Networks: Integrating Government Ratings and Crowdsourced ReportsTechnical
UrbanNav: Learning Language-Guided Embodied Urban Navigation from Web-Scale Human TrajectoriesTechnical
UrbanPG: An Efficient Framework with Personalized Context and General Backbone Interaction for Urban Spatio-Temporal LearningTechnical
Using Certifying Constraint Solvers for Generating Step-wise ExplanationsTechnical
Using Constraint Solvers to Construct Binary Codes with Good Error Correction PerformanceTechnical
Utilitarian Guarantees for the Method of Equal SharesTechnical
V-Pruner: A Fast and Globally-informed Token Pruning Framework for Vision TransformerTechnical
V2VLoc: Robust GNSS-Free Collaborative Perception via LiDAR LocalizationTechnical
VAEVQ: Enhancing Discrete Visual Tokenization Through Variational ModelingTechnical
VALIANT: Prompt Instability for Active Learning in Black-Box Medical ImagingTechnical
VBF++: Variational Bayesian Fusion with Context-Aware Priors and Recommendation-Guided Adversarial Refinement for Multimodal Video RecommendationTechnical
VCGD: Visual Clue Guided Decoding with Caption Model for Mitigating Hallucination in Multimodal Large Language ModelsTechnical
VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality EvaluationTechnical
VEDA: Generation of 3D Molecules via Variance-Exploding Diffusion with AnnealingTechnical
VFCionX: Bridging Large and Small Models for Robust Vulnerability-Fixing Commit IdentificationTechnical
VGD: Value-Guided Diffusion Toward High-Utility Medical Image SegmentationTechnical
VGGS: VGGT-guided Gaussian Splatting for Efficient and Faithful Sparse-View Surface ReconstructionTechnical
VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the WildTechnical
VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement LearningTechnical
VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy RobustnessTechnical
VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary ReconstructionTechnical
VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield ForecastingTechnical
VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object DetectionTechnical
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action ModelTechnical
VLHSA: Vision-Language Hierarchical Semantic Alignment for Jigsaw Puzzle Solving with Eroded Gaps (Student Abstract)Technical
VMChill: A Dataset for Fine-Grained Visual-Musical SynergyTechnical
VORTEX: Aligning Task Utility and Human Preferences Through LLM-Guided Reward ShapingTechnical
VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language ModelsTechnical
VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose EstimationTechnical
VPN: Visual Prompt NavigationTechnical
VPSentry: Semi-supervised Video Polyp Segmentation via Sentry-guided Long-term Prototype Fusion with Correlation Dynamic PropagationTechnical
VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement LearningTechnical
VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement LearningTechnical
VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement LearningTechnical
VSPO: Validating Semantic Pitfalls in Ontology via LLM-Based CQ GenerationTechnical
VTD-CLIP: Video-to-Text Discretization via Prompting CLIPTechnical
VTinker: Guided Flow Upsampling and Texture Mapping for High-Resolution Video Frame InterpolationTechnical
VaccineRAG: Boosting Multimodal Large Language Models’ Immunity to Harmful RAG SamplesTechnical
Value-Aligned Prompt Moderation via Zero-Shot Agentic Rewriting for Safe Image GenerationTechnical
Value-Driven Memory-Augmented Generation for Agentic LLMs: Towards Structured and Adaptive Knowledge UtilizationTechnical
Variance Computation for Weighted Model Counting with Knowledge Compilation ApproachTechnical
Variance Reduction via Resampling and Experience ReplayTechnical
Variation-Bounded Loss for Noise-Tolerant LearningTechnical
Variational OOD State Correction for Offline Reinforcement LearningTechnical
VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel SegmentationTechnical
Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor CorrectionTechnical
Venom: Liquid Diffusion-Guided Gradient Inversion for Breaking Differential Privacy in Federated LearningTechnical
Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language ModelsTechnical
VeriFlow: Modeling Distributions for Neural Network VerificationTechnical
VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across DomainsTechnical
Versatile Vision-Language Model for 3D Computed TomographyTechnical
ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMsTechnical
ViDia2Std: A Parallel Corpus and Methods for Low-Resource Vietnamese Dialect-to-Standard TranslationTechnical
ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid ReasoningTechnical
ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative PruningTechnical
ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory PredictionTechnical
ViType: High-Fidelity Visual Text Rendering via Glyph-Aware Multimodal DiffusionTechnical
Video Camera Trajectory Editing with Generative Rendering from Estimated GeometryTechnical
Video Echoed in Music: Semantic, Temporal, and Rhythmic Alignment for Video-to-Music GenerationTechnical
Video Mirror Detection with the Motion-in-Depth CueTechnical
Video SimpleQA: Towards Factuality Evaluation in Large Video Language ModelsTechnical
Video Spatial Reasoning with Object-Centric 3D RolloutTechnical
VideoChat-A1: Thinking with Long Videos by Chain-of-Shot ReasoningTechnical
VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement LearningTechnical
VietCheckMed: Explainable Regulatory Compliance Checking for Medical Advertisements on Vietnamese Social MediaTechnical
View-on-Graph: Zero-Shot 3D Visual Grounding via Vision-Language Reasoning on Scene GraphsTechnical
Views Attention Fusion of Granular-ball Fuzzy Representations Split for Improved Multi-view ClusteringTechnical
VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-useTechnical
Virtual Multiplex Staining for Histological Images Using a Marker-Wise Conditioned Diffusion ModelTechnical
VirtualEnv: A Platform for Embodied AI ResearchTechnical
VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive SystemsTechnical
Vision Transformers Are Circulant Attention LearnersTechnical
Vision-G1: Towards General Reasoning Vision-Language Models via Reinforcement LearningTechnical
Vision-Language Models Guided Graph Concept Reasoning for Interpretable Diabetic Retinopathy DiagnosisTechnical
Vision-Language Reasoning for Geolocalization: A Reinforcement Learning ApproachTechnical
Vision-MoR: Scaling Vision Transformer via Patch-Level Mixture-of-RecursionsTechnical
Vision-Only Gaussian Splatting for Collaborative Semantic Occupancy PredictionTechnical
Vision-language Incremental Learning with Dual Class-individual MemoryTechnical
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video GenerationTechnical
Vista: Scene-Aware Optimization for Streaming Video Question Answering Under Post-Hoc QueriesTechnical
Visual Bridge: Universal Visual Perception Representations GeneratingTechnical
Visual-Friendly Concept Protection via Selective Adversarial PerturbationsTechnical
VitalDiagnosis: AI-Driven Ecosystem for 24/7 Vital Monitoring and Chronic Disease ManagementTechnical
VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive InteractionTechnical
VoiceCloak: A Multi-Dimensional Defense Framework Against Unauthorized Diffusion-Based Voice CloningTechnical
Voices, Faces, and Feelings: Multi-modal Emotion-Cognition Captioning for Mental Health UnderstandingTechnical
Voting in Divisible Settings: A SurveyTechnical
VulnBench: A Comprehensive Benchmark for Transformer-Based Vulnerability DetectionTechnical
Vulnerability-Aware Robust Multimodal Adversarial TrainingTechnical
W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree SearchTechnical
WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM SafetyTechnical
WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus ImagesTechnical
WIET: Harmonizing Group-aware Model Weighting and Worker Allocation for Ensemble Temporal Prediction MaaSTechnical
WRitEer: A Multi-Objective, Preference-Driven Multi-Agent Framework for Human-Like Advanced Text GenerationTechnical
Walk Before You Dance: High-fidelity and Editable Dance Synthesis via Generative Masked Motion PriorTechnical
Walking Further: Semantic-Aware Multimodal Gait Recognition Under Long-Range ConditionsTechnical
Wasserstein-Aligned Hyperbolic Multi-View ClusteringTechnical
Wasserstein-Aware Transfer: Class-Level Alignment for Robust Diffusion Model AdaptationTechnical
WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM WatermarkingTechnical
WaveC2R: Wavelet-Driven Coarse-to-Refined Hierarchical Learning for Radar RetrievalTechnical
WaveDiST: A Wavelet Diffusion Transformer for Spatio-Temporal Estimation on Unobserved LocationsTechnical
WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided ExtrapolationTechnical
WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave EquationTechnical
Wavefront-Constrained Passive Obscured Object DetectionTechnical
Wavelet Enhanced Adaptive Frequency Filter for Sequential RecommendationTechnical
Weakest Bidder Types and New Core-Selecting Combinatorial AuctionsTechnical
Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning FrameworkTechnical
Wearable Intelligence for Healthcare Robotics: From Brain Activity to Body MovementsTechnical
Weather-Robust LiDAR Perception: Point Cloud Restoration from Adverse WeatherTechnical
WeatherEdit: Controllable Weather Editing with 4D Gaussian FieldTechnical
Weight Entropy-Maximised Evidential Metamodel for Uncertainty Quantification (Student Abstract)Technical
WeightFlow: Learning Stochastic Dynamics via Evolving Weight of Neural NetworkTechnical
Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM ReasoningTechnical
WenetSpeech-Yue: A Large-Scale Cantonese Speech Corpus with Multi-dimensional AnnotationTechnical
What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining DatasetsTechnical
What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference AlignmentTechnical
What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic StudyTechnical
What Voting Rules Actually Do: A Data-Driven Analysis of Multi-Winner VotingTechnical
What You See Is What You Reach: Towards Spatial Navigation with High-Level Human InstructionsTechnical
What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup PuzzlesTechnical
What to Trust? A Trust-aware Knowledge-guided Method for Zero-shot Object State Understanding in VideosTechnical
What, Whether and How? Unveiling Process Reward Models for Thinking with Images ReasoningTechnical
What-Meets-Where: Unified Learning of Action and Contact Localization in ImagesTechnical
When AI Meets AI: A Game-Theoretic Defense Framework Against AI Empowered Cyber ThreatsTechnical
When Equal Isn’t Fair: Mitigating Over-Normalization in Large Language Models (Student Abstract)Technical
When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?Technical
When Genes Speak: A Semantic-Guided Framework for Spatially Resolved Transcriptomics Data ClusteringTechnical
When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHFTechnical
When Instinct Guides and Insight Grounds: Staged RL Training for LLM AgentsTechnical
When Natural Strategies Meet Fuzziness and Resource-Bounded ActionsTechnical
When Person Re-Identification Meets Event Camera: A Benchmark Dataset and an Attribute-Guided Re-Identification FrameworkTechnical
When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM EditingTechnical
When Proxy Agents Disagree, Do Humans Mirror? Manipulating Human Behavior in Moral Dilemmas Through AgentsTechnical
When Reasoning Collapses: A Depth-Aware Probe into LLM Reasoning (Student Abstract)Technical
When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language ModelsTechnical
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ ToxicityTechnical
When Top-ranked Recommendations Fail: Modeling Multi-Granular Negative Feedback for Explainable and Robust Video RecommendationTechnical
When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish TrackingTechnical
When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language ModelsTechnical
When the Domain Expert Has No Time and the LLM Developer Has No Clinical Expertise: Real-World Lessons from LLM Co-Design in a Safety-Net HospitalTechnical
Where It Moves, It Matters: Referring Surgical Instrument Segmentation via MotionTechnical
Where Norms and References Collide: Evaluating LLMs on Normative ReasoningTechnical
Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context LearningTechnical
Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct PositionTechnical
WhisperDiari: A Whisper-Based Speaker Diarization Framework in Token Space Leveraging Semantic and Speaker Information for Better Text AdaptabilityTechnical
Whispering Agents: A Event-Driven Covert Communication Protocol for the Internet of AgentsTechnical
Who Is Helping Whom? Analyzing Inter-Dependencies to Evaluate Cooperation in Human-AI TeamingTechnical
Who Is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup CompetitionTechnical
Who Should I Trust? Explicit Confidence-Focused Multimodal Intent RecognitionTechnical
Whole-Body Coordination for Dynamic Object Grasping with Legged ManipulatorsTechnical
Whole-Field Action Sensing via Wearable Single-Channel EMG Sensors and Resource-Efficient Motion NetworkTechnical
Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical StudyTechnical
Why Isn’t Relational Learning Taking Over the World?Technical
Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior RecognitionTechnical
Wikatoni: An Agentic AI System for Energy Engineering WorkflowsTechnical
WikiREVIEW: A Multi-Perspective Review Framework for Automatic Wiki-Style Article GenerationTechnical
Wikontic: A Tool for Building Knowledge Graphs from Text Aligned with the Wikidata OntologyTechnical
WinMamba: Multi-Scale Shifted Windows in State Space Model for 3D Object DetectionTechnical
WingBeats and Snapshots: Fusing Sound and Vision for Mosquito Monitoring (Student Abstract)Technical
WorldAgen: Unified State-Action Prediction with Test-Time World Model TrainingTechnical
WorldGrow: Generating Infinite 3D WorldTechnical
WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous DrivingTechnical
X-MoGen: Unified Motion Generation Across Humans and AnimalsTechnical
X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and a Novel LLM-Consulted Explanation FrameworkTechnical
X-ReID: Multi-granularity Information Interaction for Video-Based Visible-Infrared Person Re-IdentificationTechnical
X-SAM: From Segment Anything to Any SegmentationTechnical
X2Edit: Revisiting Arbitrary-Instruction Image Editing Through Self-Constructed Data and Task-Aware Representation LearningTechnical
XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series Forecasting with Exogenous InputsTechnical
YOLO-IOD: Towards Real Time Incremental Object DetectionTechnical
You Don’t Need Pre-Built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning StructuresTechnical
You Only Need One Stage: Novel-View Synthesis from a Single Blind Face ImageTechnical
Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If CalibratedTechnical
Your Prompts Are Not Safe: Output-Free Membership Inference via Prompt Vectors in Vision-Language TuningTechnical
Yours or Mine? Overwriting Attacks Against Neural Audio WatermarkingTechnical
ZeRCP: Towards Communication-Efficient Collaborative Perception and Future Scene Prediction via Request-Free Spatial FilteringTechnical
Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived ModulationTechnical
Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time TrainingTechnical
Zero-Shot Robotic Manipulation via 3D Gaussian Splatting-Enhanced Multimodal Retrieval-Augmented GenerationTechnical
Zero-Shot Vision Language Reasoning via Dual-layer Scene Graph Chain of Thoughts (Student Abstract)Technical
Zero-shot Implicit Neural Manifold Representation (INMR) for Ultra-high Temporal Resolution Dynamic MRITechnical
Zero-shot Recommendation: Towards Class Semantic Relation Learning for Inferring Labels of Unseen Micro-videosTechnical
Zero-to-Hero: Empowering Video Appearance Transfer with Zero-Shot Initialization and Holistic RestorationTechnical
ZipLJP: Zipped Information Processor for Legal Judgment PredictionTechnical
Zo3T: Zero-Shot 3D-Aware Trajectory-Guided Image-to-Video Generation via Test-Time TrainingTechnical
Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification ApproachTechnical
anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task UnderstandingTechnical
db-ECBS: Interaction-Aware Multirobot Kinodynamic Motion Planning (Abstract Reprint)Technical
iCD: An Implicit Clustering Distillation Method for Structural Information Mining (Student Abstract)Technical
iDT-diet: Toward Personalized Health Forecasting-An Intelligent Digital Twin Model for Diet-Influenced Biomarker Trajectories (Student Abstract)Technical
iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM InferenceTechnical
iSeal: Encrypted Fingerprinting for Reliable LLM Ownership VerificationTechnical
mmJEPA-ECG: Cross-Posture Robust Contactless Electrocardiogram Monitoring via Millimeter Wave Radar SensingTechnical
mmPred: Radar-based Human Motion Prediction in the DarkTechnical
qa-FLoRA: Data-free query-adaptive Fusion of LoRAs for LLMsTechnical
rMMEA: Robust Multi-Modal Entity Alignment with Missing and Noise Visual ModalityTechnical
scCluBench: Comprehensive Benchmarking of Clustering Algorithms for Single-Cell RNA SequencingTechnical
uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired DataTechnical
vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMsTechnical
xMHashSeg: Cross-modal Hash Learning for Training-free Unsupervised LiDAR Semantic SegmentationTechnical
zkQML: Verifiable and Privacy-Preserving Inference for Quantum Machine Learning (Student Abstract)Technical
Δt-Mamba3D: A Time‑Aware Spatio‑Temporal State‑Space Model for Breast Cancer Risk PredictionTechnical
Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite FeedbackTechnical
‘What Do Children Think About AI?’: Insights and Educational Implications from Primary School Students’ Perceptions of AITechnical
“As Eastern Powers, I Will Veto.”: An Investigation of Nation-Level Bias of Large Language Models in International RelationsTechnical
“Debate Guru”: Honing Public Speaking Skills Among Secondary School Students with AI Tutoring SystemsTechnical

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.