Conferences · eligible papers
AAAI
2022–2026 LIVE
2026 · 4,149 papers
このEditionに反映済みのmain full research papersのみ掲載しています。著者リンクは日本の大学への著者別所属根拠がある場合に限ります。
- Infinite-Story: A Training-Free Consistent Text-to-Image Generation
日本大学: 関与なし(対象大学)
- InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer
日本大学: 関与なし(対象大学)
- InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck
日本大学: 関与なし(対象大学)
- InfoDecom: Decomposing Information for Defending Against Privacy Leakage in Split Inference
日本大学: 関与なし(対象大学)
- InfoQ: Mixed-Precision Quantization via Global Information Flow
日本大学: 関与なし(対象大学)
- Information Theoretic Optimal Surveillance for Epidemic Prevalence in Networks
日本大学: 関与なし(対象大学)
- Information-Theoretic Minimal Sufficient Representation for Multi-Domain Knowledge Graph Completion
日本大学: 関与なし(対象大学)
- Informative Subgraph Extraction with Deep Reinforcement Learning for Drug-Drug Interaction Prediction
日本大学: 関与なし(対象大学)
- Infrared-Privileged UAV Detection via Cross-Modal Vector-Quantization
日本大学: 関与なし(対象大学)
- Injection Without Distortion: Geometrically Constrained Knowledge Enhancement for Vision-Language Models
日本大学: 関与なし(対象大学)
- Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
日本大学: 関与なし(対象大学)
- Inpaint-Anywhere: Zero-Shot Multi-Identity Inpainting with Efficient Diffusion Transformer
日本大学: 関与なし(対象大学)
- Insert Anything: Image Insertion via In-Context Editing in DiT
日本大学: 関与なし(対象大学)
- Instance Dependent Testing of Samplers Using Interval Conditioning
日本大学: 関与なし(対象大学)
- Instance Generation for Meta-Black-Box Optimization Through Latent Space Reverse Engineering
日本大学: 関与なし(対象大学)
- Instance-Guided Scene Adaptation for Unsupervised Person Search
日本大学: 関与なし(対象大学)
- InstructDubber: Instruction-based Alignment for Zero-shot Movie Dubbing
日本大学: 関与なし(対象大学)
- Instruction-Guided Cross-Modal Clustering for Training-Free Visual Token Pruning in Vision-Language Models
日本大学: 関与なし(対象大学)
- InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
日本大学: 関与なし(対象大学)
- Integral-based Knockoffs Inference for Partially Linear Models
日本大学: 関与なし(対象大学)
- Integrating Diverse Assignment Strategies into DETRs
日本大学: 関与なし(対象大学)
- Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration
日本大学: 関与なし(対象大学)
- IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scenes
日本大学: 関与なし(対象大学)
- Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation
日本大学: 関与なし(対象大学)
- Intention-Aware Diffusion Model for Pedestrian Trajectory Prediction
日本大学: 関与なし(対象大学)
- Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation
日本大学: 関与なし(対象大学)
- Inter-Client Dependency Recovery with Hidden Global Components for Federated Traffic Prediction
日本大学: 関与なし(対象大学)
- InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained Features
日本大学: 関与なし(対象大学)
- InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE
日本大学: 関与なし(対象大学)
- Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks
日本大学: 関与なし(対象大学)
- Interest-Shift-Aware Logical Reasoning for Efficient Long-Sequence Recommendation
日本大学: 関与なし(対象大学)
- Interest-driven Deep Multi-modal Clustering
日本大学: 関与なし(対象大学)
- Intermediate N-Gramming: Deterministic and Fast N-Grams for Large N and Large Datasets
日本大学: 関与なし(対象大学)
- Interpolated Stochastic Interventions Based on Propensity Scores, Target Policies and Treatment-Specific Costs
日本大学: 関与なし(対象大学)
- Interpretable Reward Model via Sparse Autoencoder
日本大学: 関与なし(対象大学)
- Interpretable and Robust Behavior Abstraction via Environment-Disentangled Heterogeneous Graph
日本大学: 関与なし(対象大学)
- Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths
日本大学: 関与なし(対象大学)
- Intervention-Aware Time Series Modeling: Capturing and Evaluating Feature Dependencies
日本大学: 関与なし(対象大学)
- Intra-Class Unbiased Prototype Aggregation and Classifier Collaboration for Personalized Federated Learning
日本大学: 関与なし(対象大学)
- Intra-Image Mining and Symmetric Maximum Concept Matching for Few Shot Out-of-Distribution Detection
日本大学: 関与なし(対象大学)
- Introducing Decomposed Causality with Spatiotemporal Object-Centric Representation for Video Classification
日本大学: 関与なし(対象大学)
- Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding
日本大学: 関与なし(対象大学)
- Intuitive Thinking: Expanding Large Language Models’ Thinking for Rapid Decision-Making on Candidate Corrections in Chinese Grammar Error Correction
日本大学: 関与なし(対象大学)
- Invariant Conditional Molecular Generation Under Distribution Shift
日本大学: 関与なし(対象大学)
- Invariant Feature Learning for Counterfactual Watch-time Prediction in Video Recommendation
日本大学: 関与なし(対象大学)
- Invariant Representation Learning for Memory Behavior Modeling via Adaptive Environment Separation
日本大学: 関与なし(対象大学)
- Inverse Optimal Transport for Efficient Adaptation of Vision-Language Models
日本大学: 関与なし(対象大学)
- Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
日本大学: 関与なし(対象大学)
- Investigating Prosocial Behavior Theory in LLM Agents Under Policy-Induced Inequities
日本大学: 関与なし(対象大学)
- Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving
日本大学: 関与なし(対象大学)
- Is Symbolic Music a Specific Language? Exploring Inspiration-to-Structure Machine Composition via LLMs
日本大学: 関与なし(対象大学)
- Is Your (Reasoning) Multimodal Language Model Vulnerable Toward Distractions?
日本大学: 関与なし(対象大学)
- Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning
日本大学: 関与なし(対象大学)
- Iterative Multi-Granular RAG with Contextual Hierarchical Graph
日本大学: 関与なし(対象大学)
- JELV: A Judge of Edit-Level Validity for Evaluation and Automated Reference Expansion in Grammatical Error Correction
日本大学: 関与なし(対象大学)
- JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics
日本大学: 関与なし(対象大学)
- JoDiffusion: Jointly Diffusing Image with Pixel-Level Annotations for Semantic Segmentation Promotion
日本大学: 関与なし(対象大学)
- Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models
日本大学: 関与なし(対象大学)
- Joint Implicit and Explicit Language Learning for Pedestrian Attribute Recognition
日本大学: 関与なし(対象大学)
- Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
日本大学: 関与なし(対象大学)
- Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction
日本大学: 関与なし(対象大学)
- JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation
日本大学: 関与なし(対象大学)
- Jump-teaching: Combating Sample Selection Bias via Temporal Disagreement
日本大学: 関与なし(対象大学)
- Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search
日本大学: 関与なし(対象大学)
- Just Few States Are Enough: Randomized Sparse Feedback for Stability of Dynamical Systems
日本大学: 関与なし(対象大学)
- K-12EduBench: A Benchmark for Evaluating Large Language Models’ Knowledge, Problem-Solving, and Educational Goal Cognition in K-12 Education
日本大学: 関与なし(対象大学)
- K-ProtoDiff: Key Prototypes-Guided Diffusion for Time Series Generation
日本大学: 関与なし(対象大学)
- K-STaR: Knowledge-Aware Self-Taught Reasoner
日本大学: 関与なし(対象大学)
- KALL-E: Autoregressive Speech Synthesis with Next-Distribution Prediction
日本大学: 関与なし(対象大学)
- KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits
日本大学: 関与なし(対象大学)
- KNNDA: A New Perspective of Alignment Recovery for Partially View-Aligned Clustering
日本大学: 関与なし(対象大学)
- KPDM: Key Phrase Dynamic Masking for Robust Text-to-Image Person Retrieval
日本大学: 関与なし(対象大学)
- KPLM-STA: Physically-Accurate Shadow Synthesis for Human Relighting via Keypoint-Based Light Modeling
日本大学: 関与なし(対象大学)
- KSS-MoE: Knowledge Space Synergy Framework in Mixture of Experts for Continual Visual Instruction Tuning
日本大学: 関与なし(対象大学)
- KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
日本大学: 関与なし(対象大学)
- KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache
日本大学: 関与なし(対象大学)
- KeenKT: Knowledge Mastery-State Disambiguation for Knowledge Tracing
日本大学: 関与なし(対象大学)
- Keep On Going: Learning Robust Humanoid Motion Skills via Selective Adversarial Training
日本大学: 関与なし(対象大学)
- KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
日本大学: 関与なし(対象大学)
- Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networks
日本大学: 関与なし(対象大学)
- Key Decision-Makers in Multi-Agent Debates: Who Holds the Power?
日本大学: 関与なし(対象大学)
- Khan-GCL: Kolmogorov–Arnold Network Based Graph Contrastive Learning with Hard Negatives
日本大学: 関与なし(対象大学)
- KineST: A Kinematics-guided Spatiotemporal State Space Model for Human Motion Tracking from Sparse Signals
日本大学: 関与なし(対象大学)
- Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active Learning
日本大学: 関与なし(対象大学)
- Knowledge Boundary Discovery for Large Language Models
日本大学: 関与なし(対象大学)
- Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
日本大学: 関与なし(対象大学)
- Knowledge Graph Guided Heterogeneity-Informed Diffusion Model for Spatio-Temporal Generation
日本大学: 関与なし(対象大学)
- Knowledge-Enhanced Explainable Hypergraph Convolution Network for Medication Recommendation
日本大学: 関与なし(対象大学)
- Knowledge-Enhanced Explainable Prompting for Vision-Language Models
日本大学: 関与なし(対象大学)
- Knowledge-Enhanced Image Captioning with Adaptive Graph-based Multimodal Alignment and LLM
日本大学: 関与なし(対象大学)
- Koopman Invariants as Drivers of Emergent Time-Series Clustering in Joint-Embedding Predictive Architectures
日本大学: 関与なし(対象大学)
- Kronos: A Foundation Model for the Language of Financial Markets
日本大学: 関与なし(対象大学)
- L2-LoRA: Improving Low-Rank Adaptation with Layer-Specific Regularization
日本大学: 関与なし(対象大学)
- L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention
日本大学: 関与なし(対象大学)
- LAMDA: Two-Phase HPO via Learning Prior from Low-Fidelity Data
日本大学: 関与なし(対象大学)
- LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection
日本大学: 関与なし(対象大学)
- LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer
日本大学: 関与なし(対象大学)
- LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models
日本大学: 関与なし(対象大学)
- LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models
日本大学: 関与なし(対象大学)
- LC3: Long Cross-Language Code Clone Detection Enhanced by Opcode Sequences and Affinity Aggregation
日本大学: 関与なし(対象大学)