AAAI 2025 Accepted Papers

The full list of 3,478 papers accepted at AAAI 2025 (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: 3,478

Fine-Tuning Language Models with Collaborative and Semantic ExpertsTechnical
Fine-grained Adaptive Visual Prompt for Generative Medical Visual Question AnsweringTechnical
First Line of Defense: A Robust First Layer Mitigates Adversarial AttacksTechnical
First-Order AutomataTechnical
First-Order Federated Bilevel LearningTechnical
FlexDataset: Crafting Annotated Dataset Generation for Diverse ApplicationsTechnical
FlexPose: Pose Distribution Adaptation with Limited GuidanceTechnical
FlexiTex: Enhancing Texture Generation via Visual GuidanceTechnical
Flexible Sharpness-Aware Personalized Federated LearningTechnical
FloNa: Floor Plan Guided Embodied Visual NavigationTechnical
Flow Factorization for Efficient Generative Flow NetworksTechnical
FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest MonitoringTechnical
Focus on Local: Finding Reliable Discriminative Regions for Visual Place RecognitionTechnical
Formal Synthesis of Barrier Certificates Using Fourier Kolmogorov-Arnold NetworkTechnical
Foundation Model Driven Appearance Extraction for Robust Multiple Object TrackingTechnical
Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-MakingTechnical
Fourier Guided Adaptive Adversarial Augmentation for Generalization in Visual Reinforcement LearningTechnical
Free Lunch in the Forest: Functionally-Identical Pruning of Boosted Tree EnsemblesTechnical
Free-Moving Object Reconstruction and Pose Estimation with Virtual CameraTechnical
FreeCap: Hybrid Calibration-Free Motion Capture in Open EnvironmentsTechnical
FreeGen: Bridging Visual-Linguistic Discrepancies Towards Diffusion-based Pixel-level Data SynthesisTechnical
FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video EditingTechnical
FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision ArchitecturesTechnical
FreqTS: Frequency-Aware Token Selection for Accelerating Diffusion ModelsTechnical
Frequency-Aware Density Control via Reparameterization for High-Quality Rendering of 3D Gaussian SplattingTechnical
Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation LearningTechnical
Friends-MMC: A Dataset for Multi-modal Multi-party Conversation UnderstandingTechnical
From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-LocalizationTechnical
From Complexity to Clarity: Transforming Chest X-ray Reports with Chained Prompting (Student Abstract)Technical
From Crayons to Code: AI-Driven Insights into a Child’s Mental Health Through DrawingsTechnical
From Gambits to Assurances: Game-Theoretic Integration of Safety and Learning for Interactive RoboticsTechnical
From Large Language Models to Large Action Models: Reasoning and Planning with Physical World KnowledgeTechnical
From Representation Space to Prognostic Insights: Whole Slide Image Generation with Hierarchical Diffusion Model for Survival PredictionTechnical
From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms (Journal Track)Technical
From Your Block to Our Block: How to Find Shared Structure Between Stochastic Block Models over Multiple GraphsTechnical
Frozen Language Models Are Gradient Coherence Rectifiers in Vision TransformersTechnical
Fully-Scalable Massively Parallel Algorithm for k-center with OutliersTechnical
FunEditor: Achieving Complex Image Edits via Function Aggregation with Diffusion ModelsTechnical
Functional Connectomes of Neural NetworksTechnical
Future Sight and Tough Fights: Revolutionizing Sequential Recommendation with FENRecTechnical
Fuzzy Collaborative ReasoningTechnical
G2LDetect: A Global-to-Local Approach for Hallucination DetectionTechnical
GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle DispatchingTechnical
GAS: Generative Activation-Aided Asynchronous Split Federated LearningTechnical
GBRIP: Granular Ball Representation for Imbalanced Partial Label LearningTechnical
GCD-Sampling: A General Cross-scale Decoupled Sampling for Point CloudTechnical
GCD: Advancing Vision-Language Models for Incremental Object Detection via Global Alignment and Correspondence DistillationTechnical
GCF: Estimating Unobserved Demand Using Graph Causal ForecastingTechnical
GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion GenerationTechnical
GENTEEL-NEGOTIATOR: LLM-Enhanced Mixture-of-Expert-Based Reinforcement Learning Approach for Polite Negotiation DialogueTechnical
GEONet: Global Enhancement and Optimization Network for Lane DetectionTechnical
GHOST: Gaussian Hypothesis Open-Set TechniqueTechnical
GIST: Gear Type Identification by Spatiotemporal Trajectory Transformation for Monitoring FisheriesTechnical
GLAM: Global-Local Variation Awareness in Mamba-based World ModelTechnical
GLCF: A Global-Local Multimodal Coherence Analysis Framework for Talking Face Generation DetectionTechnical
GLEN: Generalized Focal Loss Ensemble of Low-Rank Networks for Calibrated Visual Question AnsweringTechnical
GLIC: General Format Learned Image CompressionTechnical
GMAP: Generalized Manipulation of Articulated Objects in Robotic Using Pre-trained ModelTechnical
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive LearningTechnical
GNN-Transformer Task Planning Enhanced with Semantic-Driven Data AugmentationTechnical
GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMsTechnical
GODDS: The Global Online Deepfake Detection SystemTechnical
GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISACTechnical
GRAIN: Multi-Granular and Implicit Information Aggregation Graph Neural Network for Heterophilous GraphsTechnical
GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine RegistrationTechnical
GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARLTechnical
GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph GenerationTechnical
GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-CriticTechnical
GTG: Generalizable Trajectory Generation Model for Urban MobilityTechnical
GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface ReconstructionTechnical
GaitCycFormer: Leveraging Gait Cycles and Transformers for Gait Emotion Recognition.Technical
GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image SegmentationTechnical
GarFast: Realistic and Fast Garment Transfer with a Simplified Parser-Free ApproachTechnical
GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA ImagesTechnical
Gaussian Graphical Modelling Without Independence Assumptions for Uncentered DataTechnical
GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal GuidanceTechnical
GeCC: Generalized Contrastive Clustering with Domain Shifts ModelingTechnical
GenAL: Generative Agent for Adaptive LearningTechnical
GenAuction: A Generative Auction for Online AdvertisingTechnical
GenHMR: Generative Human Mesh RecoveryTechnical
GenPlan: Generative Sequence Models as Adaptive PlannersTechnical
General Uncertainty Estimation with Delta VariancesTechnical
Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant LearningTechnical
Generalization Analysis for Deep Contrastive Representation LearningTechnical
Generalized Class Discovery in Instance SegmentationTechnical
Generalized Convergence Analysis of Tsetlin Automaton Based Algorithms: A Probabilistic Approach to Concept LearningTechnical
Generalized Debiased Semi-Supervised Hashing for Large-Scale Image RetrievalTechnical
Generalized Implicit Neural Representations for Dynamic Molecular Surface ModelingTechnical
Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic CalibrationTechnical
Generalizing Constraint Models in Constraint AcquisitionTechnical
Generating Counterfactual Explanations Under Temporal ConstraintsTechnical
Generating Synthetic Data for Unsupervised Federated Learning of Cross-Modal RetrievalTechnical
Generating Traffic Scenarios via In-Context Learning to Learn Better Motion PlannerTechnical
Generative Flow Networks for Lead Optimization in Drug Design (Student Abstract)Technical
Generative Video Diffusion for Unseen Novel Semantic Video Moment RetrievalTechnical
Genomics Data Lossless Compression with (S, K)-Mer Encoding and Deep Neural NetworksTechnical
GeoAggregator: An Efficient Transformer Model for Geo-Spatial Tabular DataTechnical
GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space ModelTechnical
GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models Through Statistically-Guided Geo-PrototypingTechnical
Geodesic Flow Kernels for Semi-Supervised Learning on Mixed-Variable Tabular DatasetTechnical
Geometry-Aware 3D Salient Object Detection NetworkTechnical
Germane Conflicts: Desirable Properties for Localising InconsistencyTechnical
Ghidorah: Towards Robust Multi-Scale Information Diffusion Prediction via Test-Time TrainingTechnical
GigaGS: 3D Gaussian Based Planar Representation for Large-Scene Surface ReconstructionTechnical
Giving Cars Eyes: Using Computer Vision to Prevent Road Traffic Accidents in NigeriaTechnical
Global Attribute-Association Pattern Aggregation for Graph Fraud DetectionTechnical
Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view ClusteringTechnical
Global-Semantic Alignment Distillation for Partial Multi-view ClassificationTechnical
GlyphSR: A Simple Glyph-Aware Framework for Scene Text Image Super-ResolutionTechnical
GoBERT: Gene Ontology Graph Informed BERT for Universal Gene Function PredictionTechnical
GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic ExpressionsTechnical
Goal-Driven Reasoning in DatalogMTL with Magic SetsTechnical
GradQ-ViT: Robust and Efficient Gradient Quantization for Vision TransformersTechnical
Gradient-Based Nonlinear Rehearsal Learning with Multivariate AlterationsTechnical
Gradient-Based Sample Selection for Black-Box Universal Domain AdaptationTechnical
Gradient-Guided Credit Assignment and Joint Optimization for Dependency-Aware Spatial CrowdsourcingTechnical
Granularity-Adaptive Spatial Evidence Tokenization for Video Question AnsweringTechnical
Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial ResilienceTechnical
Graph Consistency and Diversity Measurement for Federated Multi-View ClusteringTechnical
Graph Contrastive Learning with Joint Spectral Augmentation of Attribute and TopologyTechnical
Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural NetworksTechnical
Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature ScalesTechnical
Graph Structure Refinement with Energy-based Contrastive LearningTechnical
GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian ExpertsTechnical
Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending Against Poisoning AttacksTechnical
Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition EstimationTechnical
GuideNER: Annotation Guidelines Are Better than Examples for In-Context Named Entity RecognitionTechnical
Guided and Variance-Corrected Fusion with One-shot Style Alignment for Large-Content Image GenerationTechnical
HDLayout: Hierarchical and Directional Layout Planning for Arbitrary Shaped Visual Text GenerationTechnical
HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge PartitioningTechnical
HEROS-GAN: Honed-Energy Regularized and Optimal Supervised GAN for Enhancing Accuracy and Range of Low-Cost AccelerometersTechnical
HFF-Tracker: A Hierarchical Fine-grained Fusion Tracker for Referring Multi-Object TrackingTechnical
HHAN: Comprehensive Infectious Disease Source Tracing via Heterogeneous Hypergraph Neural NetworkTechnical
HI-DR: Exploiting Health Status-Aware Attention and an EHR Graph+ for Effective Medication RecommendationTechnical
HLMEA: Unsupervised Entity Alignment Based on Hybrid Language ModelsTechnical
HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data AugmentationTechnical
HOIMamba: Efficient Mamba-based Disentangled Progressive Learning for HOI DetectionTechnical
HSOD-BIT-V2: A Challenging Benchmark for Hyperspectral Salient Object DetectionTechnical
HSRDiff: A Hierarchical Self-Regulation Diffusion Model for Stochastic Semantic SegmentationTechnical
HUANG: A Robust Diffusion Model-based Targeted Adversarial Attack Against Deep Hashing RetrievalTechnical
HVAdam: A Full-Dimension Adaptive OptimizerTechnical
HVDualformer: Histogram-Vision Dual Transformer for White BalanceTechnical
HYBOOD: A Hybrid Generative Model for Out-of-Distribution Detection with Corruption EstimationTechnical
HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated LearningTechnical
Harmonious Music-driven Group Choreography with Trajectory-Controllable DiffusionTechnical
Harnessing Event Sensory Data for Error Pattern Prediction in Vehicles: A Language Model ApproachTechnical
Harnessing Language Model for Cross-Heterogeneity Graph Knowledge TransferTechnical
Harnessing Robust Statistics for Trustworthy AITechnical
Hateful Meme Detection through Context-Sensitive Prompting and Fine-Grained Labeling (Student Abstract)Technical
HePa: Heterogeneous Graph Prompting for All-Level Classification TasksTechnical
Hedging and Approximate Truthfulness in Traditional Forecasting CompetitionsTechnical
HeterGP: Bridging Heterogeneity in Graph Neural Networks with Multi-View PromptingTechnical
Heterogeneous Graph Neural Network on Semantic TreeTechnical
Heterogeneous Multi-Agent Bandits with Parsimonious HintsTechnical
Heterogeneous Multi-Robot Graph Coverage with Proximity and Movement ConstraintsTechnical
Heterogeneous Prompt-Guided Entity Inferring and Distilling for Scene-Text Aware Cross-Modal RetrievalTechnical
Heuristic-free Knowledge Distillation for Streaming ASR via Multi-modal TrainingTechnical
HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain AdaptationTechnical
HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement UnitsTechnical
Hide Exposures by Removing Mastermind’s External Sources on Social Network (Student Abstract)Technical
HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion ModelsTechnical
Hierarchical Consensus Network for Multiview Feature LearningTechnical
Hierarchical Cross-Modal Alignment for Open-Vocabulary 3D Object DetectionTechnical
Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical EvaluationTechnical
Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological OscillationsTechnical
Hierarchical Mixture of Experts: Generalizable Learning for High-Level SynthesisTechnical
Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center ClustersTechnical
Hierarchical Multi-Source Uncertainty Aggregation for Interactive Video CaptioningTechnical
Hierarchical Vector Quantization for Unsupervised Action SegmentationTechnical
Hierarchically-Structured Open-Vocabulary Indoor Scene Synthesis with Pre-trained Large Language ModelTechnical
High School Course Scheduling: Student Preferences and Fairness Constraints (Student Abstract)Technical
High-Fidelity Polarimetric Implicit 3D Reconstruction with View-Dependent Physical RepresentationTechnical
High-Resolution Frame Interpolation with Patch-based Cascaded DiffusionTechnical
Higher Order Structures for Graph ExplanationsTechnical
Highly Efficient Rotation-Invariant Spectral Embedding for Scalable Incomplete Multi-View ClusteringTechnical
Highly Imperceptible Black-Box Graph Injection Attacks with Reinforcement LearningTechnical
Highly Parallelized Reinforcement Learning Training with Relaxed Assignment DependenciesTechnical
Holistic Correction with Object Prototype for Video Object SegmentationTechnical
Holistic Semantic Representation for Navigational Trajectory GenerationTechnical
HomeDiffusion: Zero-Shot Object Customization with Multi-View Representation Learning for Indoor ScenesTechnical
HomoMatcher: Achieving Dense Feature Matching with Semi-Dense Efficiency by Homography EstimationTechnical
HoneypotNet: Backdoor Attacks Against Model ExtractionTechnical
Hotspotter: A Generalizable Pipeline for Automated Detection of Subtle Volcanic Thermal Features in Satellite ImagesTechnical
How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function LearningTechnical
How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?Technical
How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct MatchingTechnical
How to Re-enable PDE Loss for Physical Systems Modeling Under Partial ObservationTechnical
Hubness Change Point DetectionTechnical
Human Interpretable Virtual Metrology in the Semiconductor ManufacturingTechnical
Human and AI Perceptual Differences in Image Classification ErrorsTechnical
Human-Computer Interaction for AI Systems Design: Reflections on an Online Course on Human-AI Interaction for ProfessionalsTechnical
Hybrid Data-Free Knowledge DistillationTechnical
Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster ConvergenceTechnical
Hybrid Phenology Modeling for Predicting Temperature Effects on Tree DormancyTechnical
Hybrid Quantum-Classical Style Transfer (Student Abstract)Technical
Hybrid Reasoning About Relative Position and Orientation of Objects and Navigating Agents Using Answer Set ProgrammingTechnical
Hybrid-Driving: An Autonomous Driving Decision Framework Integrating Large Language Models, Knowledge Graphs and Driving RulesTechnical
HybridReg: Robust 3D Point Cloud Registration with Hybrid MotionsTechnical
Hyper-Spectral Image Generation from Frequency SpectrumsTechnical
HyperDefender: A Robust Framework for Hyperbolic GNNsTechnical
HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series ForecastingTechnical
Hyperbolic-Constraint Point Cloud Reconstruction from Single RGB-D ImagesTechnical
Hypergraph Learning for Unsupervised Graph Alignment via Optimal TransportTechnical
Hypernetwork Approach to Bayesian MAML (Student Abstract)Technical
Hyperparametric Robust and Dynamic Influence MaximizationTechnical
IBAS:Imperceptible Backdoor Attacks in Split Learning with Limited InformationTechnical
ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content ModerationTechnical
ID-GMLM: Intelligent Decision-Making with Integrated Graph Models and Large Language ModelsTechnical
ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait ImageTechnical
IDseq: Decoupled and Sequentially Detecting and Grounding Multi-Modal Media ManipulationTechnical
IMQC: A Large Language Model Platform for Medical Quality ControlTechnical
IOHunter: Graph Foundation Model to Uncover Online Information OperationsTechnical
IOP: An Idempotent-Like Optimization Method on the Pareto Front of HypernetworkTechnical
IPVTON: Image-based 3D Virtual Try-on with Image Prompt AdapterTechnical
IRMamba: Pixel Difference Mamba with Layer Restoration for Infrared Small Target DetectionTechnical
ISPDiffuser: Learning RAW-to-sRGB Mappings with Texture-Aware Diffusion Models and Histogram-Guided Color ConsistencyTechnical
ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPOTechnical
IWRN:A Robust Blind Watermarking Method for Artwork Image Copyright Protection Against Noise AttackTechnical
Identifying Query-Relevant Neurons in Large Language Models for Long-Form TextsTechnical
Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language ModelsTechnical
Image-to-video Adaptation with Outlier Modeling and Robust Self-learningTechnical
ImagePiece: Content-aware Re-tokenization for Efficient Image RecognitionTechnical
Imagine: Image-Guided 3D Part Assembly with Structure Knowledge GraphTechnical
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text DetectionTechnical
Imitation Learning Backoff: Reinforcement Learning-based Channel Access for Guaranteeing Fairness (Student Abstract)Technical
Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video CaptioningTechnical
Implicit Relative Labeling-Importance Aware Multi-Label Metric LearningTechnical
Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency ParsingTechnical
Improved Approximation Algorithms for Clustered TSP and Subgroup PlanningTechnical
Improved Bounds for Online Facility Location with PredictionsTechnical
Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax OptimizationTechnical
Improved Regret Bounds for Online Fair Division with Bandit LearningTechnical
Improving Cancer Gene Prediction by Enhancing Common Information Between the PPI Network and Gene Functional AssociationTechnical
Improving Community-Participated Patrol for Anti-PoachingTechnical
Improving Cooperation in Language Games with Bayesian Inference and the Cognitive HierarchyTechnical
Improving Deep Learning Speed and Performance Through Synaptic Neural BalanceTechnical
Improving Federated Domain Generalization Through Dynamical Weights Calculated from Data Influences on Global Model UpdateTechnical
Improving Generalization for AI-Synthesized Voice DetectionTechnical
Improving Generalization in Offline Reinforcement Learning via Latent Distribution Representation LearningTechnical
Improving Model Probability Calibration by Integration of Large Data Sources with Biased LabelsTechnical
Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge AugmentationTechnical
Improving Natural Language Understanding for LLMs via Large-Scale Instruction SynthesisTechnical
Improving Private Random Forest Prediction Using Matrix RepresentationTechnical
Improving Transformer Based Line Segment Detection with Matched Predicting and Re-rankingTechnical
Improving the Lower Bound in Branch-and-Bound Algorithms for MaxSATTechnical
In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via SearchTechnical
In-Context Policy Adaptation via Cross-Domain Skill DiffusionTechnical
In-context Prompt-augmented Micro-video Popularity PredictionTechnical
In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing ImagesTechnical
Inapproximability of Optimal Multi-Agent Pathfinding ProblemsTechnical
Incentives for Early ArrivalTechnical
Incident Diagnosing and Reporting System Based on Retrieval Augmented Large Language ModelTechnical
Incomplete Multi-View Multi-Label Classification via Diffusion-Guided Redundancy RemovalTechnical
Incomplete Multi-view Clustering via Diffusion Contrastive GenerationTechnical
Incomplete and Unpaired Multi-View Graph Clustering with Cross-View Feature FusionTechnical
Incongruent Multimodal Federated Learning for Medical Vision and Language-based Multi-label Disease DetectionTechnical
Increasing Revenue in Efficient Combinatorial Auctions by Learning to Generate Artificial CompetitionTechnical
Incremental Nyström-based Multiple Kernel ClusteringTechnical
Individually Stable Dynamics in Coalition Formation over GraphsTechnical
Inductive Learning of Logical Theories with LLMs: A Expressivity-graded AnalysisTechnical
Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-IdentificationTechnical
Infinite-Canvas: Higher-Resolution Video Outpainting with Extensive Content GenerationTechnical
Influence-Based Fair Selection for Sample-Discriminative Backdoor AttackTechnical
Information-Theoretic Generative Clustering of DocumentsTechnical
Inheriting Generalized Learngene for Efficient Knowledge Transfer across Multiple TasksTechnical
IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization PerspectiveTechnical
InpDiffusion: Image Inpainting Localization via Conditional Diffusion ModelsTechnical
InstantPainting: Expanding GANs for Efficient Text-Conditioned Image Generation PlatformTechnical
InstantSticker: Realistic Decal Blending via Disentangled Object ReconstructionTechnical
Instruct Where the Model Fails: Generative Data Augmentation via Guided Self-contrastive Fine-tuningTechnical
InstructOCR: Instruction Boosting Scene Text SpottingTechnical
Int*-Match: Balancing Intra-Class Compactness and Inter-Class Discrepancy for Semi-Supervised Speaker RecognitionTechnical
Int2Planner: An Intention-based Multi-modal Motion Planner for Integrated Prediction and PlanningTechnical
InteDisUX: Intepretation-Guided Discriminative User-Centric Explanation for Time SeriesTechnical
Integrating Co-Training with Edge Discrimination to Enhance Graph Neural Networks Under HeterophilyTechnical
Integrating Inference and Experimental Design for Contextual Behavioral Model LearningTechnical
Integrating Large Language Models and Möbius Group Transformations for Temporal Knowledge Graph Embedding on the Riemann SphereTechnical
Integrating Low-Level Visual Cues for Enhanced Unsupervised Semantic SegmentationTechnical
Integrating Multi-Source Data for Long Sequence Precipitation ForecastingTechnical
Integrating Personalized Spatio-Temporal Clustering for Next POI RecommendationTechnical
Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised LearningTechnical
Intelligent Clinical Assistant for Personalized Responses and Clinical SummariesTechnical
Intent Oriented Contrastive Learning for Sequential RecommendationTechnical
Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language ModelsTechnical
Interpretable Failure Detection with Human-Level ConceptsTechnical
Interweaving Memories of a Siamese Large Language ModelTechnical
Intra and Inter Parser-Prompted Transformers for Effective Image RestorationTechnical
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective SurfacesTechnical
InvSeg: Test-Time Prompt Inversion for Semantic SegmentationTechnical
InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-InstructTechnical
Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain AdaptationTechnical
Investigating Relational State Abstraction in Collaborative MARLTechnical
Investigating and Mitigating Undesirable Biases in Large Language ModelsTechnical
Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News DetectionTechnical
Is Poisoning a Real Threat to DPO? Maybe More So Than You ThinkTechnical
Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene PerceptionTechnical
Is Your Image a Good Storyteller?Technical
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word EmphasisTechnical
Iterative Counterfactual Data AugmentationTechnical
Iterative Self-Training with Class-Aware Text-to-Image Synthesis for Visual Task LearningTechnical
Iterative Sparse Attention for Long-sequence RecommendationTechnical
J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal DomainTechnical
JAQ: Joint Efficient Architecture Design and Low-Bit Quantization with Hardware-Software Co-ExplorationTechnical
JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMsTechnical
JoVALE: Detecting Human Actions in Video Using Audiovisual and Language ContextsTechnical
Joint Class-level and Instance-level Relationship Modeling for Novel Class DiscoveryTechnical
Joint Knowledge Editing for Information Enrichment and Probability PromotionTechnical
Joint Scoring Rules: Competition Between Agents Avoids Performative PredictionTechnical
Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced RelevanceTechnical
Just a Few Glances: Open-Set Visual Perception with Image Prompt ParadigmTechnical
K-ON: Stacking Knowledge on the Head Layer of Large Language ModelTechnical
K-hop Hypergraph Neural Network: A Comprehensive Aggregation ApproachTechnical
KAES: Multi-aspect Shared Knowledge Finding and Aligning for Cross-prompt Automated Scoring of Essay TraitsTechnical
KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep HashingTechnical
KD-MSLRT: Lightweight Sign Language Recognition Model Based on Mediapipe and 3D to 1D Knowledge DistillationTechnical
KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection ModelsTechnical
KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal RankTechnical
KOALA: Kernel Coupling and Element Imputation Induced Multi-View ClusteringTechnical
Kernel Learning for Sample Constrained Black-Box OptimizationTechnical
Kernel Representation Learning for Time Sequence: Algorithm, Theory, and ApplicationsTechnical
KernelMatmul: Scaling Gaussian Processes to Large Time SeriesTechnical
KeyGS: A Keyframe-Centric Gaussian Splatting Method for Monocular Image SequencesTechnical
KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive KeypointsTechnical
Knockoffs Inference for Partially Linear Models with Automatic Structure DiscoveryTechnical
Know Where You Are From: Event-Based Segmentation via Spatio-Temporal PropagationTechnical
Know2Vec: A Black-Box Proxy for Neural Network RetrievalTechnical
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question AnsweringTechnical
Knowledge Graph Completion with Relation-Aware Anchor EnhancementTechnical
Knowledge Graph and Large Language Model for MetabolomicsTechnical
Knowledge Is Power: Harnessing Large Language Models for Enhanced Cognitive DiagnosisTechnical
Knowledge-Enhanced Hierarchical Heterogeneous Graph for Personality Identification with Limited Training DataTechnical
Knowledge-Guided Domain Adaptation Model for Transferring Drug Response Prediction from Cell Lines to PatientsTechnical
Knowledge-Infused Learning for Developing a Mental Health Diagnostic Copilot in Healthcare SystemsTechnical
Knowledge-driven Scientific Large Language ModelsTechnical
Kolmogorov-Arnold Networks Still Catastrophically Forget but Differently from MLPTechnical
L-Man: A Large Multi-modal Model Unifying Human-centric TasksTechnical
L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text CompressionTechnical
LAGD: Local Topological-Alignment and Global Semantic-Deconstruction for Incremental 3D Semantic SegmentationTechnical
LAMA-UT: Language Agnostic Multilingual ASR Through Orthography Unification and Language-Specific TransliterationTechnical
LAqua: Laplacian Pyramids for Aquatic Segmentation (Student Abstract)Technical
LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised DebiasingTechnical
LIBA: Language Instructed Multi-granularity Bridge Assistant for 3D Visual GroundingTechnical
LLM Agents Can Be Choice-Supportive Biased Evaluators: An Empirical StudyTechnical
LLM Stinger: Jailbreaking LLMs Using RL Fine-Tuned LLMs (Student Abstract)Technical
LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge GraphsTechnical
LLM-based Online Prediction of Time-varying Graph Signals (Student Abstract)Technical
LLM4RSR: Large Language Models as Data Correctors for Robust Sequential RecommendationTechnical
LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential RecommendationTechnical
LLMs in the Classroom: Outcomes and Perceptions of Questions Written with the Aid of AITechnical
LOHA: Direct Graph Spectral Contrastive Learning Between Low-Pass and High-Pass ViewsTechnical
LPCG: A Self-conditional Architecture for Labeled Point Cloud GenerationTechnical
LRM-LLaVA: Overcoming the Modality Gap of Multilingual Large Language-Vision Model for Low-Resource LanguagesTechnical
LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based RecommendationTechnical
LTLf Synthesis on First-Order Agent Programs in Nondeterministic EnvironmentsTechnical
LVPTrack: High Performance Domain Adaptive UAV Tracking with Label Aligned Visual Prompt TuningTechnical
Label Aggregation for Composite Crowd Tasks by Worker Ability Constraint SatisfactionTechnical
Label Noise Correction via Fuzzy Learning MachineTechnical
Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac FluoroscopyTechnical
Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio ManagementTechnical
Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with AttributionTechnical
Language Pre-training Guided Masking Representation Learning for Time Series ClassificationTechnical
Large Images Are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian SplattingTechnical
Large Language Models Are Read/Write Policy-Makers for Simultaneous GenerationTechnical
Large Language Models Enhanced Personalized Graph Neural Architecture Search in Federated LearningTechnical
Large-Scale School Mapping Using Weakly Supervised Deep Learning for Universal School ConnectivityTechnical
Last-iterate Convergence in Regularized Graphon Mean Field GameTechnical
Latent Diffusion-Enhanced Virtual Try-On via Optimized Pseudo-Label GenerationTechnical
LayerAct: Advanced Activation Mechanism for Robust Inference of CNNsTechnical
Layered-Parameter Perturbation for Zeroth-Order Optimization of Optical Neural NetworksTechnical
Learn How to Query from Unlabeled Data Streams in Federated LearningTechnical
Learning Causal Transition Matrix for Instance-dependent Label NoiseTechnical
Learning Complexity of Gradient Descent and Conjugate Gradient AlgorithmsTechnical
Learning Concept Prerequisite Relation via Global Knowledge Relation OptimizationTechnical
Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional ResponsesTechnical
Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule GenerationTechnical
Learning Dynamic Similarity by Bidirectional Hierarchical Sliding Semantic Probe for Efficient Text Video RetrievalTechnical
Learning Fine-Grained Alignment for Aerial Vision-Dialog NavigationTechnical
Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional TheoryTechnical
Learning Hierarchical Task Knowledge for PlanningTechnical
Learning Joint Behaviors with Large VariationsTechnical
Learning Local Neighborhoods of Non-Gaussian Graphical ModelsTechnical
Learning More Expressive General Policies for Classical Planning DomainsTechnical
Learning Multiple User Distributions for Recommendation via Guided Conditional DiffusionTechnical
Learning Nash Equilibrium of Markov Potential Games with a Shared Constraint via Primal-Dual OptimizationTechnical
Learning Optimal Auctions with Correlated Value DistributionsTechnical
Learning Regularization for Graph Inverse ProblemsTechnical
Learning Robust and Privacy-Preserving Representations via Information TheoryTechnical
Learning Set Functions with Implicit DifferentiationTechnical
Learning Strategy Representation for Imitation Learning in Multi-Agent GamesTechnical
Learning Structural Causal Models from Ordering: Identifiable Flow ModelsTechnical
Learning Structured World Models From and For Physical InteractionsTechnical
Learning Theorem Rationale for Improving the Mathematical Reasoning Capability of Large Language ModelsTechnical
Learning Together Securely: Prototype-Based Federated Multi-Modal Hashing for Safe and Efficient Multi-Modal RetrievalTechnical
Learning Valid Dual Bounds in Constraint Programming: Boosted Lagrangian Decomposition with Self-Supervised LearningTechnical
Learning Verified Safe Neural Network Controllers for Multi-Agent Path FindingTechnical
Learning Visually Grounded Domain Ontologies via Embodied Conversation and ExplanationTechnical
Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text CorrectionTechnical
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss RescalingTechnical
Learning from Summarized Data: Gaussian Process Regression with Sample Quasi-LikelihoodTechnical
Learning to Collaborate with Unknown Agents in the Absence of RewardTechnical
Learning to Rewind via Iterative Prediction of Past Weights for Practical UnlearningTechnical
Learning to Think like a Neuron in Middle SchoolTechnical
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation SpaceTechnical
Learnware Specification via Label-Aware Neural EmbeddingTechnical
Less Is More: Token Context-Aware Learning for Object TrackingTechnical
Leveraging Anatomical Consistency for Multi-Object Detection in Ultrasound Images via Source-free Unsupervised Domain AdaptationTechnical
Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual ProcessingTechnical
Leveraging Attention to Effectively Compress Prompts for Long-Context LLMsTechnical
Leveraging Computer Vision and Visual LLMs for Cost-Effective and Consistent Street Food Safety Assessment in Kolkata IndiaTechnical
Leveraging Constraint Violation Signals for Action Constrained Reinforcement LearningTechnical
Leveraging First and Zeroth-Order Gradient to Address Imbalanced Black-Box Prompt Tuning via Minimax OptimizationTechnical
Leveraging Human Input to Enable Robust, Interactive, and Aligned AI SystemsTechnical
Leveraging Textual Memory and Key Frame Reasoning for Full Video Understanding Using Off-the-Shelf LLMs and VLMs (Student Abstract)Technical
Leveraging the Dual Capabilities of LLM: LLM-Enhanced Text Mapping Model for Personality DetectionTechnical
LiD-FL: Towards List-Decodable Federated LearningTechnical
LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic DataTechnical
Lifelong Scalable Generative System via Online Maximum Mean DiscrepancyTechnical
Lifting Scheme-Based Implicit Disentanglement of Emotion-Related Facial Dynamics in the WildTechnical
LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge GraphTechnical
Lightweight Contrastive Distilled Hashing for Online Cross-modal RetrievalTechnical
Lightweight Yet Fine-Grained: A Graph Capsule Convolutional Network with Subspace Alignment for Shared-Account Sequential RecommendationTechnical
Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy GradingTechnical
Linear Decoding of Morphology Relations in Language Models (Student Abstract)Technical
Linear Equations with Min and Max Operators: Computational ComplexityTechnical
Linear Streaming Bandit: Regret Minimization and Fixed-Budget Epsilon-Best Arm IdentificationTechnical
Linking Industry Sectors and Financial Statements: A Hybrid Approach for Company ClassificationTechnical
List Update with PredictionTechnical
LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math ReasoningTechnical
Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised LearningTechnical
LoGoFair: Post-Processing for Local and Global Fairness in Federated LearningTechnical
LoRA Unlearns More and Retains More (Student Abstract)Technical
Local Causal Discovery Without Causal SufficiencyTechnical
Local Causal Discovery for Structural Evidence of Direct DiscriminationTechnical
Locally Convex Global Loss Network for Decision-Focused LearningTechnical
Logarithmic Regret for Linear Markov Decision Processes with Adversarial CorruptionsTechnical
Logic Induced High-Order Reasoning Network for Event-Event Relation ExtractionTechnical
Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based TuningTechnical
Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to TailTechnical
Long-Term EEG Partitioning for Seizure Onset DetectionTechnical
Look Around Before Locating: Considering Content and Structure Information for Visual GroundingTechnical
Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter TuningTechnical
Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLMTechnical
Loosely Synchronized Rule-Based Planning for Multi-Agent Path Finding with Asynchronous ActionsTechnical
M2Flow: A Motion Information Fusion Framework for Enhanced Unsupervised Optical Flow Estimation in Autonomous DrivingTechnical
M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology ImagesTechnical
M3Net: Efficient Time-Frequency Integration Network with Mirror Attention for Audio Classification on EdgeTechnical
M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous DrivingTechnical
MABR: Multilayer Adversarial Bias Removal Without Prior Bias KnowledgeTechnical
MAFT: Multimodal Automated Fact-Checking via TextualizationTechnical
MAMS: Model-Agnostic Module Selection Framework for Video CaptioningTechnical
MASS: Overcoming Language Bias in Image-Text MatchingTechnical
MATWA: A Web Toolkit for Matching Under PreferencesTechnical
MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token TransformerTechnical
MDFG: Multi-Dimensional Fine-Grained Modeling for Fatigue DetectionTechnical
ME: Modelling Ethical Values for Value AlignmentTechnical
MEATRD: Multimodal Anomalous Tissue Region Detection Enhanced with Spatial TranscriptomicsTechnical
MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic DialoguesTechnical
MEPNet: Medical Entity-Balanced Prompting Network for Brain CT Report GenerationTechnical
MFL-Owner: Ownership Protection for Multi-modal Federated Learning via Orthogonal Transform WatermarkTechnical
MHBench: Demystifying Motion Hallucination in VideoLLMsTechnical
MI-CAPTCHA: Enhance the Security of CAPTCHA Using Mooney ImagesTechnical
MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music CompositionTechnical
MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic ClassificationTechnical
MIMTrack: In-Context Tracking via Masked Image ModelingTechnical
ML-GOOD: Towards Multi-Label Graph Out-Of-Distribution DetectionTechnical
MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural CollapseTechnical
MM-Mixing: Multi-Modal Mixing Alignment for 3D UnderstandingTechnical
MM-Tracker: Motion Mamba for UAV-platform Multiple Object TrackingTechnical
MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language ModelsTechnical
MMPF: Multi-Modal Perception Framework for Abnormal Medical Condition DetectionTechnical
MOCID: Motion Context and Displacement Information Learning for Moving Infrared Small Target DetectionTechnical
MORE: Molecule Pretraining with Multi-Level Pretext TaskTechnical
MP: Endowing Large Language Models with Lateral ThinkingTechnical
MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series ClassificationTechnical
MRBTP: Efficient Multi-Robot Behavior Tree Planning and CollaborationTechnical
MRR-FV: Unlocking Complex Fact Verification with Multi-Hop Retrieval and ReasoningTechnical
MSAmba: Exploring Multimodal Sentiment Analysis with State Space ModelsTechnical
MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion RecognitionTechnical
MSR: A Multifaceted Self-Retrieval Framework for Microscopic Cascade PredictionTechnical
MSSDA: Multi-Sub-Source Domain Adaptation for Diabetic Foot Neuropathy RecognitionTechnical
MSV-PCT: Multi-Sparse-View Enhanced Transformer Framework for Salient Object Detection in Point CloudsTechnical
MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge TranslationTechnical
MUCD: Unsupervised Point Cloud Change Detection via Masked ConsistencyTechnical
MUN: Image Forgery Localization Based on M³ Encoder and UN DecoderTechnical
MVREC: A General Few-shot Defect Classification Model Using Multi-View Region-ContextTechnical
MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human PreferencesTechnical
MYOPIA: Protecting Face Privacy from Malicious Personalized Text-to-Image Synthesis via Unlearnable ExamplesTechnical
M^3EL: A Multi-task Multi-topic Dataset for Multi-modal Entity LinkingTechnical
MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual LearningTechnical
Maintaining Fairness in Logit-based Knowledge Distillation for Class-Incremental LearningTechnical
Making Large Vision Language Models to Be Good Few-Shot LearnersTechnical
Making Transparency Advocates: An Educational Approach Towards Better Algorithmic Transparency in PracticeTechnical
MalDetectFormer: Leveraging Sparse SpatioTemporal Information for Effective Malicious Traffic DetectionTechnical
Mamba-CAD: State Space Model for 3D Computer-Aided Design Generative ModelingTechnical
Manhattan Self-Attention Diffusion Residual Networks with Dynamic Bias Rectiﬁcation for BCI-based Few-Shot LearningTechnical
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-SequenceTechnical
Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language ModelsTechnical
Marginal Benefit Driven RL Teacher for Unsupervised Environment DesignTechnical
Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation LearningTechnical
MarkovType: A Markov Decision Process Strategy for Non-Invasive Brain-Computer Interfaces Typing SystemsTechnical
MaskPrompt: Open-Vocabulary Affordance Segmentation with Object Shape Mask PromptsTechnical
MaskViM: Domain Generalized Semantic Segmentation with State Space ModelsTechnical
Matching While Perceiving: Enhance Image Feature Matching with Applicable Semantic AmalgamationTechnical
MathMistake Checker: A Comprehensive Demonstration for Step-by-Step Math Problem Mistake Finding by Prompt-Guided LLMsTechnical
Max-Mahalanobis Anchors Guidance for Multi-View ClusteringTechnical
Maximizing Signal in Human-Model Preference AlignmentTechnical
Maximizing the Position Embedding for Vision Transformers with Global Average PoolingTechnical
McHirc: A Multimodal Benchmark for Chinese Idiom Reading ComprehensionTechnical
Measuring Cross-Modal Interactions in Multimodal ModelsTechnical
Measuring Fine-Grained Urban Air Temperature with Satellite ImageryTechnical
Mechanism Design for Connecting Regions Under DisruptionsTechnical
Mediation Analysis for Probabilities of CausationTechnical
Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal TriggersTechnical
Memory Efficient Matting with Adaptive Token RoutingTechnical
Memory-Augmented Re-Completion for 3D Semantic Scene CompletionTechnical
Memory-Reduced Meta-Learning with Guaranteed ConvergenceTechnical
Mental-Perceiver: Audio-Textual Multi-Modal Learning for Estimating Mental DisordersTechnical
MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and ModalitiesTechnical
Merging Mechanisms for Ads and Organic Items in E-commerce PlatformsTechnical
MerryQuery: A Trustworthy LLM-Powered Tool Providing Personalized Support for Educators and StudentsTechnical
Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function SpaceTechnical
MetaNeRV: Meta Neural Representations for Videos with Spatial-Temporal GuidanceTechnical
MetaSymNet: A Tree-like Symbol Network with Adaptive Architecture and Activation FunctionsTechnical
Metric Distortion of Line-up Elections: The Right Person for the Right JobTechnical
Metric-Agnostic Continual Learning for Sustainable Group FairnessTechnical
Micro-macro Wavelet-based Gaussian Splatting for 3D Reconstruction from Unconstrained ImagesTechnical
MicroFiberDetect: An Application for the Detection of Microfibres in Wastewater Sludge Based on CNNsTechnical
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention SimilarityTechnical
Mind Individual Information! Principal Graph Learning for Multimedia RecommendationTechnical
Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies Between Model Predictions and Human Responses in VQATechnical
MindPainter: Efficient Brain-Conditioned Painting of Natural Images via Cross-Modal Self-Supervised LearningTechnical
Minimal Change in Modal Logic S5Technical
Mining In-distribution Attributes in Outliers for Out-of-distribution DetectionTechnical
Mitigating Bias in Machine Learning: A Comprehensive Review and Novel ApproachesTechnical
Mitigating Feature Gap for Adversarial Robustness by Feature DisentanglementTechnical
Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information FlowTechnical
Mitigating Pervasive Modality Absence Through Multimodal Generalization and RefinementTechnical
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent FrameworkTechnical
Mixed-Curvature Multi-Modal Knowledge Graph CompletionTechnical
Mixture of Experts as Representation Learner for Deep Multi-View ClusteringTechnical
Mixture of Knowledge Minigraph Agents for Literature Review GenerationTechnical
Mixture of Online and Offline Experts for Non-Stationary Time SeriesTechnical
Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack DetectionTechnical
Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive DiffusionTechnical
MoLE:Decoding by Mixture of Layer Experts Alleviates Hallucination in Large Vision-Language ModelsTechnical
Mobility Data Representations for Spatiotemporal TasksTechnical
Modality-Aware Shot Relating and Comparing for Video Scene DetectionTechnical
Model AI Assignments 2025Technical
Model Lineage Closeness AnalysisTechnical
ModelDiff: Symbolic Dynamic Programming for Model-Aware Policy Transfer in Deep Q-LearningTechnical
Modeling All Response Surfaces in One for Conditional Search SpacesTechnical
Modeling Latent Non-Linear Dynamical System over Time SeriesTechnical
Modular-Cam: Modular Dynamic Camera-view Video Generation with LLMTechnical
Momentum Pseudo-Labeling for Weakly Supervised Phrase GroundingTechnical
Monitoring Primitive Interactions During the Training of DNNsTechnical
Moonshine: Distilling Game Content Generators into Steerable Generative ModelsTechnical
Motif-Oriented Representation Learning with Topology Refinement for Drug-Drug Interaction PredictionTechnical
Motif-aware Graph Neural Networks for Networked Time Series ImputationTechnical
MotifGPL: Motif-Enhanced Graph Prototype Learning for Deciphering Urban Social SegregationTechnical
Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion ModelTechnical
Motion Decoupled 3D Gaussian Splatting for Dynamic Object RepresentationTechnical
Motion Prior Knowledge Learning with Homogeneous Language Descriptions for Moving Infrared Small Target DetectionTechnical
Motion-Zero: A Zero-Shot Trajectory Control Framework of Moving Object for Diffusion-Based Video GenerationTechnical
Motion-adaptive Transformer for Event-based Image DeblurringTechnical
Move and Act: Enhanced Object Manipulation and Background Integrity for Image EditingTechnical
Multi-Apartment Rent DivisionTechnical
Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian PerspectiveTechnical
Multi-Branch Self-Drafting for LLM Inference AccelerationTechnical
Multi-Edge Reinforced Collaborative Data Acquisition for Continuous Video Analytics by Prioritizing Quality over QuantityTechnical
Multi-Focus Image Fusion via Explicit Defocus Blur ModellingTechnical
Multi-Frame Deformable Look-Up Table for Compressed Video Quality EnhancementTechnical
Multi-Granular Multimodal Clue Fusion for Meme UnderstandingTechnical
Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision BoundaryTechnical
Multi-Granularity Video Object SegmentationTechnical
Multi-Instance Multi-Label Classification from Crowdsourced LabelsTechnical
Multi-Label Few-Shot Image Classification via Pairwise Feature Augmentation and Flexible Prompt LearningTechnical
Multi-Label Ranking Loss Minimization for Matrix CompletionTechnical
Multi-Modal Hand-to-Mouth Gesture Recognition in Activity-Oriented RGB-Thermal Footage (Student Abstract)Technical
Multi-Modal Latent Variables for Cross-Individual Primary Visual Cortex Modeling and AnalysisTechnical
Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality ConstraintsTechnical
Multi-OphthaLingua: A Multilingual Benchmark for Assessing and Debiasing LLM Ophthalmological QA in LMICsTechnical
Multi-Perspective Consolidation Enhanced Cognitive Diagnosis via Conditional Diffusion ModelTechnical
Multi-Scale Graph Learning for Anti-Sparse DownscalingTechnical
Multi-Shape Matching with Cycle Consistency Basis via Functional MapsTechnical
Multi-StyleGS: Stylized Gaussian Splatting with Multiple StylesTechnical
Multi-Subspace Matrix Recovery from Permuted DataTechnical
Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual RecognitionTechnical
Multi-Turn Jailbreaking Large Language Models via Attention ShiftingTechnical
Multi-View 3D Human Pose Estimation with Weakly Synchronized ImagesTechnical
Multi-View Collaborative Learning Network for Speech Deepfake DetectionTechnical
Multi-View Empowered Structural Graph Wordification for Language ModelsTechnical
Multi-View Multi-Label Classification via View-Label Matching SelectionTechnical
Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic DatasetTechnical
Multi-View Unsupervised Column Subset Selection via Combinatorial Search (Student Abstract)Technical
Multi-aspect Self-guided Deep Information Bottleneck for Multi-modal ClusteringTechnical
Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image RestorationTechnical
Multi-concept Model Immunization through Differentiable Model MergingTechnical
Multi-fingered Hand Grasps with Visuo-Tactile Fusion via Multi-Agent Deep Reinforcement LearningTechnical
Multi-label Self Knowledge DistillationTechnical
Multi-modal Deepfake Detection via Multi-task Audio-Visual Prompt LearningTechnical
Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird RecognitionTechnical
Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive LearningTechnical
Multi-type MOOCs Recommendation: Leveraging Deep Multi-Relational Representation and Hierarchical ReasoningTechnical
Multi-view Consistent 3D Panoptic Scene UnderstandingTechnical
Multi-view Evidential Learning-based Medical Image SegmentationTechnical
Multi-view Granular-ball Contrastive ClusteringTechnical
MultiSFL: Towards Accurate Split Federated Learning via Multi-Model Aggregation and Knowledge ReplayTechnical
Multimodal Fine-Grained Apparent Personality Trait Recognition: Joint Modeling of Big Five and Questionnaire Item-level ScoresTechnical
Multimodal Fusion Using Multi-View Domains for Data Heterogeneity in Federated LearningTechnical
Multimodal Hypothetical Summary for Retrieval-based Multi-image Question AnsweringTechnical
Multimodal Promptable Token Merging for Diffusion ModelsTechnical
Multimodal Variational Autoencoder: A Barycentric ViewTechnical
Multiple Feature Refining Network for Visual Emotion Distribution LearningTechnical
Multiple Mean-Payoff Optimization Under Local Stability ConstraintsTechnical
Multiple Purchase Chains with Negative Transfer Elimination for Multi-Behavior RecommendationTechnical
Multiple Trade-offs: An Improved Approach for Lexicographic Linear BanditsTechnical
Multiplex Graph Representation Learning with Homophily and ConsistencyTechnical
Multisensory Machine IntelligenceTechnical
Multispectral Pedestrian Detection with Sparsely Annotated LabelTechnical
Muses: 3D-Controllable Image Generation via Multi-Modal Agent CollaborationTechnical
M²N: A Progressive Macro-to-Micro 3D Modeling Scheme for Unveiling Drug-Target AffinityTechnical
M²RL-Net: Multi-View and Multi-Level Relation Learning Network for Weakly-Supervised Image Forgery DetectionTechnical
NAAM: Node-Aware Attention Mechanism for Distilling GNNs-to-MLP (Student Abstract)Technical
NBA3D: Neighbor-Based Confidence Adjustment for 3D Rare Object Detection Using LiDARTechnical
NOMATTERXAI: Generating “No Matter What” Alterfactual Examples for Explaining Black-Box Text Classification ModelsTechnical
NaFV-Net: An Adversarial Four-view Network for Mammogram ClassificationTechnical
Natural Language Generation with Expert StandardsTechnical
NaviFormer: A Spatio-Temporal Context-Aware Transformer for Object NavigationTechnical
Navigating Towards Fairness with Data SelectionTechnical
Neighborhood-Aware Negative Sampling for Student Knowledge and Behavior ModelingTechnical
Network Inversion of Convolutional Neural Nets (Student Abstract)Technical
Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View ImagesTechnical
Neural Block Compression: Variable Bitrates Feature Blocks for Texture RepresentationTechnical
Neural Combinatorial Clustered Bandits for Recommendation SystemsTechnical
Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling ProblemsTechnical
Neural Conformal Control for Time Series ForecastingTechnical
Neural Conjugate Flows: A Physics-Informed Architecture with Flow StructureTechnical
Neural Control and Certificate Repair via Runtime MonitoringTechnical
Neural Networks Perform Sufficient Dimension ReductionTechnical
Neural Reasoning for Sure Through Constructing Explainable ModelsTechnical
Neural Temporal Point Processes for Forecasting Directional Relations in Evolving HypergraphsTechnical
Neuro-Guided Graph Search for Symbolic Regression (Student Abstract)Technical
Neuron Explanations for Conformal Prediction (Student Abstract)Technical
Neurons to Words: A Novel Method for Automated Neural Network Interpretability and AlignmentTechnical
Neurosymbolic Reinforcement Learning: Playing MiniHack with Probabilistic Logic ShieldsTechnical
New Compilation Languages Based on Restricted Weak DecomposabilityTechnical
NightReID: A Large-Scale Nighttime Person Re-Identification BenchmarkTechnical
No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier MethodsTechnical
Noise-Injected Spiking Graph Convolution for Energy-Efficient 3D Point Cloud DenoisingTechnical
NoiseHGNN: Synthesized Similarity Graph-Based Neural Network for Noised Heterogeneous Graph Representation LearningTechnical
Noisy Correspondence Rectification via Asymmetric Similarity LearningTechnical
Noisy Label Calibration for Multi-View ClassificationTechnical
Non-Convex Tensor Recovery from Local MeasurementsTechnical
Non-stochastic Budgeted Online Pricing with Semi-Bandit FeedbackTechnical
Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective ScenesTechnical
Normalize Then Propagate: Efficient Homophilous Regularization for Few-Shot Semi-Supervised Node ClassificationTechnical
Novel View Synthesis Under Large-Deviation Viewpoint for Autonomous DrivingTechnical
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement LearningTechnical
Nuance Matters: Probing Epistemic Consistency in Causal ReasoningTechnical
Number Theoretic Accelerated Learning of Physics-Informed Neural NetworksTechnical
OAC: Output-adaptive Calibration for Accurate Post-training QuantizationTechnical
OAMaskFlow: Occlusion-Aware Motion Mask for Scene FlowTechnical
OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language RecognitionTechnical
OODML: Whole Slide Image Classification Meets Online Pseudo-Supervision and Dynamic Mutual LearningTechnical
OT-StainNet: Optimal Transport Driven Semantic Matching for Weakly Paired H&E-to-IHC Stain TransferTechnical
OTIAS: OcTree Implicit Adaptive Sampling for Multispectral and Hyperspectral Image FusionTechnical
OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse ProblemsTechnical
OTPNet: ODE-inspired Tuning-free Proximal Network for Remote Sensing Image FusionTechnical
OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive ProblemTechnical
ObjVariantEnsemble: Advancing Point Cloud LLM Evaluation in Challenging Scenes with Subtly Distinguished ObjectsTechnical
Occlusion-Embedded Hybrid Transformer for Light Field Super-ResolutionTechnical
Occlusion-Insensitive Talking Head Video Generation via Facelet CompensationTechnical
Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy OptimizationTechnical
Offline Safe Reinforcement Learning Using Trajectory ClassificationTechnical
Omni-Query Active Learning for Source-Free Domain Adaptive Cross-Modality 3D Semantic SegmentationTechnical
OmniMark: Efficient and Scalable Latent Diffusion Model FingerprintingTechnical
On Action Theories with Iterable First-Order ProgressionTechnical
On Designing the Optimal Integrated Ad Auction in E-commerce PlatformsTechnical
On Finding Hubs in High Dimensions with SamplingTechnical
On Local Overfitting and Forgetting in Deep Neural NetworksTechnical
On Probabilistic Truncation in Privacy-preserving Machine LearningTechnical
On Shallow Planning Under Partial ObservabilityTechnical
On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABsTechnical
On the Expressiveness and Length Generalization of Selective State Space Models on Regular LanguagesTechnical
On the Hardness of Training Deep Neural Networks DiscretelyTechnical
On the Logic of Theory Base Change: Reformulation of Belief BasesTechnical
On the Modelling of Constraints with Tractable Logical OperatorsTechnical
On the Power of Randomization for Obviously Strategy-Proof MechanismsTechnical
On the Robustness of Distributed Machine Learning Against Transfer AttacksTechnical
On-Policy Algorithms for Continual Reinforcement Learning (Student Abstract)Technical
OnAIR: Applications of the NASA On-Board Artificial Intelligence Research PlatformTechnical
One for Dozens: Adaptive REcommendation for All Domains with Counterfactual AugmentationTechnical
One-Shot Reference-based Structure-Aware Image to Sketch SynthesisTechnical
OneBatchPAM: A Fast and Frugal K-Medoids AlgorithmTechnical
Online Fraud Detection via Test-Time Retrieval-Based Representation EnrichmentTechnical
Online Learning of Coalition Structures by Selfish AgentsTechnical
Online MDP with Prototypes Information: A Robust Adaptive ApproachTechnical
Online Nonsubmodular Optimization with Delayed Feedback in the Bandit SettingTechnical
Online Prompt Selection for Program SynthesisTechnical
Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain AlignmentTechnical
Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and AlgorithmTechnical
Open-World Multimodal Understanding and Generation with Efficiently Finetuned Foundation ModelsTechnical
Open-world Radio Frequency Fingerprint Identification via Augmented Semi-supervised LearningTechnical
OpenViewer: Openness-Aware Multi-View LearningTechnical
Optimal Auction Design for Mixed BiddersTechnical
Optimal Bounds for Dissatisfaction in Perpetual VotingTechnical
Optimal Classification Trees for Continuous Feature Data Using Dynamic Programming with Branch-and-BoundTechnical
Optimal Control Operator Perspective and a Neural Adaptive Spectral MethodTechnical
Optimal Viewpoint Selection for Autonomous Photography Using Reinforcement LearningTechnical
Optimal and Efficient Binary Questioning for Accelerated AnnotationTechnical
Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning ApproachTechnical
Optimising Spatial Teamwork Under UncertaintyTechnical
Optimized Gradient Clipping for Noisy Label LearningTechnical
Optimized Random Features for the Neural Tangent Kernel (Student Abstract)Technical
Optimizing Gene-Based Testing for Antibiotic Resistance PredictionTechnical
Optimizing Heat Alert Issuance with Reinforcement LearningTechnical
Optimizing Label Assignment for Weakly Supervised Person SearchTechnical
Optimizing Quantized Diffusion Models via Distillation with Cross-Timestep Error CorrectionTechnical
Orpheus: Engineering Multiagent Systems via Communicating AgentsTechnical
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video DiffusionTechnical
Out-of-Distribution Detection with Prototypical Outlier ProxyTechnical
Out-of-Distribution Generalization on Graphs via Progressive InferenceTechnical
Overcoming Heterogeneous Data in Federated Medical Vision-Language Pre-training: A Triple-Embedding Model Selector ApproachTechnical
PA3Fed: Period-Aware Adaptive Aggregation for Improved Federated LearningTechnical
PBECount: Prompt-Before-Extract Paradigm for Class-Agnostic CountingTechnical
PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic SegmentationTechnical
PCM Selector: Penalized Covariate-Mediator Selection Operator for Evaluating Linear Causal EffectsTechnical
PDBs Go Numeric: Pattern-Database Heuristics for Simple Numeric PlanningTechnical
PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor ScenesTechnical
PEIE: Physics Embedded Illumination Estimation for Adaptive DehazingTechnical
PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar ClassifiersTechnical
PHR-DIFF: Portrait Highlights Removal via Patch-aware Diffusion ModelTechnical
POI Recommendation via Multi-Objective Adversarial Imitation LearningTechnical
POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation LearningTechnical
POPoS: Improving Efficient and Robust Facial Landmark Detection with Parallel Optimal Position SearchTechnical
PRIORITY2REWARD: Incorporating Healthworker Preferences for Resource Allocation PlanningTechnical
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial AttacksTechnical
PScalpel: A Machine Learning-based Guider for Protein Phase-Separating Behaviour AlterationTechnical
PUBLICSPEAK: Hearing the Public with a Probabilistic FrameworkTechnical
PVTree: Realistic and Controllable Palm Vein Generation for Recognition TasksTechnical
Paid with Models: Optimal Contract Design for Collaborative Machine LearningTechnical
Pamba: Enhancing Global Interaction in Point Clouds via State Space ModelTechnical
Pancreatic Cancer Diagnosis SystemTechnical
PanoDiT: Panoramic Videos Generation with Diffusion TransformerTechnical
Parallel Greedy Best-First Search with a Bound on Expansions Relative to Sequential SearchTechnical
Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITATechnical
Parameterized Complexity of Caching in NetworksTechnical
Parametric ρ-Norm Scaling CalibrationTechnical
Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-offTechnical
Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential DiscountingTechnical
Partial Label Causal Representation Learning for Instance-Dependent Supervision and Domain GeneralizationTechnical
Partial Point Cloud Registration with Multi-view 2D Image LearningTechnical
Path-Adaptive Matting for Efficient Inference Under Various Computational Cost ConstraintsTechnical
PerReactor: Offline Personalised Multiple Appropriate Facial Reaction GenerationTechnical
Personalized Clustering via Targeted Representation LearningTechnical
Personalized Dynamic Music Emotion Recognition with Dual-Scale Attention-Based Meta-LearningTechnical
Personalized Label Inference Attack in Federated Transfer Learning via Contrastive Meta LearningTechnical
Personalized Learning in Action: Exploring AI and Robotics for Early Childhood EducationTechnical
PersonalizedUS: Interpretable Breast Cancer Risk Assessment with Local Coverage Uncertainty QuantificationTechnical
Persuasion for Social Good: How to Build and Break AITechnical
Perturbating, Tuning, and Collaborating: Harnessing Vision Foundation Models for Single Domain Generalization on Medical ImagingTechnical
Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech DeepfakesTechnical
PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial AttackTechnical
PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object DetectionTechnical
PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological MeasurementTechnical
Physical Marker: Revealing Invisible Hyperlinks Hidden in Printed TrademarksTechnical
Physical-aware Neural Radiance Fields for Efficient Exposure CorrectionTechnical
Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River NetworksTechnical
Pic2Prep: A Multimodal Conversational Agent for Cooking AssistanceTechnical
Pioneering Explainable Video Fact-Checking with a New Dataset and Multi-role Multimodal Model ApproachTechnical
PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and GenerationTechnical
PlaNet: Learning to Mitigate Atmospheric Turbulence in Planetary ImagesTechnical
Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language NavigationTechnical
Plug-and-Play Tri-Branch Invertible Block for Image RescalingTechnical
PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud CompletionTechnical
PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space ModelTechnical
PokerBench: Training Large Language Models to Become Professional Poker PlayersTechnical
Polarization Guided Mask-Free Shadow RemovalTechnical
Political Bias Prediction Models Focus on Source Cues, Not SemanticsTechnical
Poplar: Efficient Scaling of Distributed DNN Training on Heterogeneous GPU ClustersTechnical
Population Aware Diffusion for Time Series GenerationTechnical
Portcullis: A Scalable and Verifiable Privacy Gateway for Third-Party LLM InferenceTechnical
Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal DatasetTechnical
PoseLLaVA: Pose Centric Multimodal LLM for Fine-Grained 3D Pose ManipulationTechnical
Position-Aware Guided Point Cloud Completion with CLIP ModelTechnical
Power of Diversity: Enhancing Data-Free Black-Box Attack with Domain-Augmented LearningTechnical
Practical Offloading for Fine-Tuning LLM on Commodity GPU via Learned Sparse ProjectorsTechnical
Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse ViewsTechnical
Pre-Assignment Problem for Unique Minimum Vertex Cover on Bounded Clique-Width GraphsTechnical
Pre-Trained Vision-Language Models as Noisy Partial AnnotatorsTechnical
Pre-Training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information BottleneckTechnical
Pre-trained Behavioral Model for Malicious User Prediction on Social PlatformTechnical
Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose EstimationTechnical
PrecipDiff: Leveraging Image Diffusion Models to Enhance Satellite-Based Precipitation ObservationsTechnical
Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized PromptsTechnical
Predicting the Original Appearance of Damaged Historical DocumentsTechnical
Prediction-Based Adaptive Variable Ordering Heuristics for Constraint Satisfaction ProblemsTechnical
Predictive Modeling of Homeless Service Assignment: A Representation Learning ApproachTechnical
Preference-Oriented Supervised Fine-Tuning: Favoring Target Model over Aligned Large Language ModelsTechnical
Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)Technical
PriFold: Biological Priors Improve RNA Secondary Structure PredictionsTechnical
Prior-Constrained Association Learning for Fine-Grained Generalized Category DiscoveryTechnical
Prior-guided Hierarchical Harmonization Network for Efficient Image DehazingTechnical
PrivDNFIS: Privacy-preserving and Efficient Deep Neuro-Fuzzy Inference SystemTechnical
Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine LearningTechnical
Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion ModelsTechnical
Privacy-Preserving V2X Collaborative Perception Integrating Unknown CollaboratorsTechnical
Privacy-and-Utility-Aware Publishing of SchedulesTechnical
ProPose: Probabilistic 3D Human Pose Estimation with Instance-Level Distribution and Normalizing FlowTechnical
Proactive and Reactive Constraint Programming for Stochastic Project Scheduling with Maximal Time-LagsTechnical
Probabilistic Forecasting of Irregularly Sampled Time Series with Missing Values via Conditional Normalizing FlowsTechnical
Probabilistic Shielding for Safe Reinforcement LearningTechnical
Probabilistic Strategy Logic with Degrees of ObservabilityTechnical
Probability-Density-aware Semi-supervised LearningTechnical
Procedure Knowledge Decoupled Distillation Strategy for Procedure Planning in Instructional VideosTechnical
Progressive Distribution Matching for Federated Semi-Supervised LearningTechnical
Progressive Self-Learning for Domain Adaptation on Symbolic Regression of Integer SequencesTechnical
Promising Multi-Granularity Linguistic Steganography by Jointing Syntactic and Lexical ManipulationsTechnical
Promoting Knowledge Base Question Answering by Directing LLMs to Generate Task-relevant Logical FormsTechnical
Prompt Tuning In a Compact Attribute SpaceTechnical
Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single Image DenoisingTechnical
Prompt-based Unifying Inference Attack on Graph Neural NetworksTechnical
PromptDet: A Lightweight 3D Object Detection Framework with LiDAR PromptsTechnical
PromptHaze: Prompting Real-world Dehazing via Depth Anything ModelTechnical
Proof Simulation via Round-based Strategy Extraction for QBFTechnical
Proportionally Fair Makespan ApproximationTechnical
Proportionally Fair Matching via Randomized RoundingTechnical
ProsodyTalker: 3D Visual Speech Animation via Prosody DecompositionTechnical
Protecting Model Adaptation from Trojans in the Unlabeled DataTechnical
ProtoArgNet: Interpretable Image Classification with Super-Prototypes and ArgumentationTechnical
ProtoCar: Learning 3D Vehicle Prototypes from Single-View and Unconstrained Driving Scene ImagesTechnical
ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query DecoderTechnical
Prototype-Guided Multimodal Relation Extraction based on Entity AttributesTechnical
Prototypical Replay with Old-class Focusing Knowledge Distillation for Incremental Named Entity RecognitionTechnical
Provably Secure Image Robust Steganography via Cross-modal Error CorrectionTechnical
Pseudo Informative Episode Construction for Few-Shot Class-Incremental LearningTechnical
Public Opinion Field Effect and Hawkes Process Join Hands for Information Popularity PredictionTechnical
Pushing the Limits of BFP on Narrow Precision LLM InferenceTechnical
Q-MAML: Quantum Model-Agnostic Meta-Learning for Variational Quantum AlgorithmsTechnical
QAagent: A Multiagent System for Unit Test Generation via Natural Language Pseudocode (Student Abstract)Technical
QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation PlatformTechnical
QiMLP: Quantum-inspired Multilayer Perceptron with Strong Correlation Mining and Parameter CompressionTechnical
QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language ModelsTechnical
QuARF: Quality-Adaptive Receptive Fields for Degraded Image PerceptionTechnical
Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion ModelsTechnical
Quality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data CurationTechnical
Quantitative Predictive Monitoring and Control for Safe Human-Machine InteractionTechnical
Quantum Best Arm Identification with Quantum OraclesTechnical
Quantum-inspired Non-homologous Representation Constraint Mechanism for Long-tail Senses of Word Sense DisambiguationTechnical
Queries, Representation & Detection: The Next 100 Model Fingerprinting SchemesTechnical
Query Quantized Neural SLAMTechnical
Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-CaptioningTechnical
Query-efficient Attack for Black-box Image Inpainting Forensics via Reinforcement LearningTechnical
Question-guided Insights Generation for Automated Exploratory Data AnalysisTechnical
Quickest Detection of Adversarial Attacks Against Correlated EquilibriaTechnical
R-DTI: Drug Target Interaction Prediction Based on Second-Order Relevance ExplorationTechnical
RA-GAR: A Richly Annotated Benchmark for Gait Attribute RecognitionTechnical
RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype LearningTechnical
RAGG: Retrieval-Augmented Grasp Generation ModelTechnical
RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-ResolutionTechnical
RATT: A Thought Structure for Coherent and Correct LLM ReasoningTechnical
RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text RewritingTechnical
RDPI: A Refine Diffusion Probability Generation Method for Spatiotemporal Data ImputationTechnical
REGNav: Room Expert Guided Image-Goal NavigationTechnical
REM: A Scalable Reinforced Multi-Expert Framework for Multiplex Influence MaximizationTechnical
REPEAT: Improving Uncertainty Estimation in Representation Learning ExplainabilityTechnical
RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model ReusabilityTechnical
REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative ProximityTechnical
RFL: Simplifying Chemical Structure Recognition with Ring-Free LanguageTechnical
RILQ: Rank-Insensitive LoRA-Based Quantization Error Compensation for Boosting 2-Bit Large Language Model AccuracyTechnical
RMath: A Logic Reasoning-Focused Datasets Toward Mathematical Multistep Reasoning TasksTechnical
RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial AttackTechnical
RRT-MVS: Recurrent Regularization Transformer for Multi-View StereoTechnical
RUNA: Object-Level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal RepresentationsTechnical
R^2-Art: Category-Level Articulation Pose Estimation from Single RGB Image via Cascade Render StrategyTechnical
Rapid Learning in Constrained Minimax Games with Negative MomentumTechnical
Rare Event Detection in Imbalanced Multi-Class Datasets Using an Optimal MIP-Based Ensemble Weighting ApproachTechnical
ReFF: Reinforcing Format Faithfulness in Language Models Across Varied TasksTechnical
ReMask-Animate: Refined Character Image Animation Using Mask-Guided AdaptersTechnical
ReMoGPT: Part-Level Retrieval-Augmented Motion-Language ModelsTechnical
ReactGPT: Understanding of Chemical Reactions via In-Context TuningTechnical
Ready for You When You Are Back: Content-Driven Session-Based Recommendation for Continuity of ExperienceTechnical
Real-Time Calibration Model for Low-Cost Sensor in Fine-Grained Time SeriesTechnical
Real-Time Neural Denoising with Render-Aware Knowledge DistillationTechnical
Real-Time Object Detection and Skeletonization for Motion Prediction in Video StreamingTechnical
RealPortrait: Realistic Portrait Animation with Diffusion TransformersTechnical
Realizing AI for Impact: Towards Participatory Human-AI Collaboration for Water Conservation and Reproductive HealthTechnical
Reasoning over Uncertain Text by Generative Large Language ModelsTechnical
Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature SelectionTechnical
Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot LearningTechnical
Recoverable Facial Identity Protection via Adaptive Makeup Transfer Adversarial AttacksTechnical
Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield NetworksTechnical
Recursive Aggregates as Intensional Functions in Answer Set Programming: Semantics and Strong EquivalenceTechnical
Reducing AUV Energy Consumption Through Dynamic Sensor Directions Switching via Deep Reinforcement LearningTechnical
Reducing Divergence in Batch Normalization for Domain AdaptationTechnical
Reducing Leximin Fairness to Utilitarian OptimizationTechnical
RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression ComprehensionTechnical
Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document RecognitionTechnical
Refine then Classify: Robust Graph Neural Networks with Reliable Neighborhood Contrastive RefinementTechnical
RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised LearningTechnical
Region-aware Difference Distilling with Attribute-guided Contrastive Regularization for Change CaptioningTechnical
Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and LocalizationTechnical
Reinforcement Active Client Selection for Federated Heterogeneous Graph LearningTechnical
Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion FiltersTechnical
Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language ModelsTechnical
Relaxed Rotational Equivariance via G-Biases in VisionTechnical
Reliable Uncertainty Quantification in Machine Learning via Conformal PredictionTechnical
Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from NeighborsTechnical
RemDet: Rethinking Efficient Model Design for UAV Object DetectionTechnical
RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face RecognitionTechnical
RepeatLeakage: Leak Prompts from Repeating as Large Language Model Is a Good RepeaterTechnical
Replacing Paths with Connection-Biased Attention for Knowledge Graph CompletionTechnical
Replication-proof Bandit Mechanism Design with Bayesian AgentsTechnical
Representation Learning Based Predicate Invention on Knowledge GraphsTechnical
Representation Learning: A Causal PerspectiveTechnical
Representation Space Augmentation for Effective Self-Supervised Learning on Tabular DataTechnical
Representation-driven Option Discovery in Reinforcement LearningTechnical
Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold FrameworkTechnical
Reputation-aware Revenue Allocation for Auction-based Federated LearningTechnical
Residual Diffusion Deblurring Model for Single Image Defocus DeblurringTechnical
Resource Constrained Pathfinding with Enhanced Bidirectional A* SearchTechnical
Responsibility-aware Strategic Reasoning in Probabilistic Multi-Agent SystemsTechnical
Responsive Dynamic Graph Disentanglement for Metro Flow ForecastingTechnical
Restabilizing Diffusion Models with Predictive Noise Fusion Strategy for Image Super-ResolutionTechnical
Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation PerspectiveTechnical
Rethinking High-speed Image Reconstruction Framework with Spike CameraTechnical
Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation LearningTechnical
Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image DenoisingTechnical
Rethinking U-Net: Task-Adaptive Mixture of Skip Connections for Enhanced Medical Image SegmentationTechnical
Rethinking and Improving Student Learning and Forgetting Processes for Attention based Knowledge Tracing ModelsTechnical
Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream TasksTechnical
RetouchGPT: LLM-based Interactive High-Fidelity Face Retouching via Imperfection PromptingTechnical
Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search EnginesTechnical
Retrieving Versus Understanding Extractive Evidence in Few-Shot LearningTechnical
Revelations: A Decidable Class of POMDPs with Omega-Regular ObjectivesTechnical
Reverse Distribution Based Video Moment Retrieval for Effective Bias EliminationTechnical
Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity LinkingTechnical
Revisiting CAD Model Generation by Learning Raster SketchTechnical
Revisiting Change Captioning from Self-supervised Global-Part AlignmentTechnical
Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance PerspectiveTechnical
Revisiting Interpolation for Noisy Label CorrectionTechnical
Revisiting Tampered Scene Text Detection in the Era of Generative AITechnical
Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph ModelTechnical
Rewind and Render: Towards Factually Accurate Text-to-Video Generation with Distilled Knowledge RetrievalTechnical
Riemannian Geometric-based Meta LearningTechnical
RingFormer: A Ring-Enhanced Graph Transformer for Organic Solar Cell Property PredictionTechnical
Risk Controlled Image RetrievalTechnical
Risk-averse Total-reward MDPs with ERM and EVaRTechnical
RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label NoiseTechnical
RoPaSS: Robust Watermarking for Partial Screen-Shooting ScenariosTechnical
Robots Learning Through Physical Interactive IntelligenceTechnical
Robust Graph Based Social Recommendation Through Contrastive Multi-View LearningTechnical
Robust Heterogeneous Graph Classification for Molecular Property Prediction with Information BottleneckTechnical
Robust Image Hashing Based on Contrastive Masked Autoencoder with Weak-Strong Augmentation AlignmentTechnical
Robust Logit Adjustment for Learning with Long-Tailed Noisy DataTechnical
Robust Multi-Objective Preference Alignment with Online DPOTechnical
Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy LabelsTechnical
Robust and Adaptive AI Models for Medication Usage Forecasting Using ICD-9/10 Code (Student Abstract)Technical
Robust and Consistent Online Video Instance Segmentation via Instance Mask PropagationTechnical
Rule-Guided Graph Neural Networks for Explainable Knowledge Graph ReasoningTechnical
S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural FieldTechnical
S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical ImagingTechnical
SADBA: Self-Adaptive Distributed Backdoor Attack Against Federated LearningTechnical
SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot SegmentationTechnical
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise RobustnessTechnical
SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge DetectionTechnical
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation SteeringTechnical
SCCS: Deep Neural Spectral Clustering for Self-Supervised Subcellular Structure SegmentationTechnical
SDAS: Semantic Data Acquisition System for Minimizing Redundancy and Maximizing DiversityTechnical
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language ModelsTechnical
SGDiff: Scene Graph Guided Diffusion Model for Image Collaborative SegCaptioningTechnical
SGFormer: Semantic-Geometry Fusion Transformer for Multi-modal 3D Panoptic SegmentationTechnical
SIDE: Socially Informed Drought Estimation Toward Understanding Societal Impact Dynamics of Environmental CrisisTechnical
SIDL: A Real-World Dataset for Restoring Smartphone Images with Dirty LensesTechnical
SIGMA: Selective Gated Mamba for Sequential RecommendationTechnical
SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus ImageTechnical
SLACE: A Monotone and Balance-Sensitive Loss Function for Ordinal RegressionTechnical
SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image PretrainingTechnical
SLR-MVTC: Smooth Low-Rank Multi-View Tensor ClusteringTechnical
SLRL: Semi-Supervised Local Community Detection Based on Reinforcement LearningTechnical
SMLE: Safe Machine Learning via Embedded OverapproximationTechnical
SMR-Net: Semantic-Guided Mutually Reinforcing Network for Cross-Modal Image Fusion and Salient Object DetectionTechnical
SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive LearningTechnical
SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to BranchTechnical
SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene UnderstandingTechnical
SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph CompletionTechnical
SPACETIME: Causal Discovery from Non-Stationary Time SeriesTechnical
SPASCA: Social Presence and Support with Conversational Agent for Persons Living with DementiaTechnical
SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery NetworkTechnical
SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning TasksTechnical
SRDC: Semantics-based Ransomware Detection and Classification with LLM-assisted Pre-trainingTechnical
SSAN: A Symbol Spatial-Aware Network for Handwritten Mathematical Expression RecognitionTechnical
SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image ReconstructionTechnical
SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAMTechnical
SSL-STMFormer Self-Supervised Learning Spatio-Temporal Entanglement Transformer for Traffic Flow PredictionTechnical
SSLFusion: Scale and Space Aligned Latent Fusion Model for Multimodal 3D Object DetectionTechnical
SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-SharpeningTechnical
ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training DataTechnical
ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal ForecastingTechnical
STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological CounselingTechnical

AAAI accepted papers in other years

AAAI 2026 (4,902)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.