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。
- Learning from Guidelines: Structured Prompt Optimization for Expert Annotation Tasks
日本大学: 関与なし(対象大学)
- Learning from Human Gaze: Human-like Robot Social Navigation in Dense Crowds
日本大学: 関与なし(対象大学)
- Learning from Imperfect Data: Robust Inference of Dynamic Systems Using Simulation-Based Generative Model
日本大学: 関与なし(対象大学)
- Learning from Long-Term Engagement: Adaptive Tutoring Dialogue Planning for Personalized Education
日本大学: 関与なし(対象大学)
- Learning from Reasoning Failures via Synthetic Data Generation
日本大学: 関与なし(対象大学)
- Learning from Scoring Disagreements: Contrastive Error Mining for Efficient and Robust LLM-based Assessment
日本大学: 関与なし(対象大学)
- Learning from the Undesirable: Robust Adaptation of Language Models Without Forgetting
日本大学: 関与なし(対象大学)
- Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions
日本大学: 関与なし(対象大学)
- Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation
日本大学: 関与なし(対象大学)
- Learning to Cluster Rare Cell Types: Implicit Semantic Data Augmentation for Spatial Multi-modal Omics Analysis
日本大学: 関与なし(対象大学)
- Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation
日本大学: 関与なし(対象大学)
- Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation
日本大学: 関与なし(対象大学)
- Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
日本大学: 関与なし(対象大学)
- Learning to Cooperate with Minimal Observability
日本大学: 関与なし(対象大学)
- Learning to Curate Context: Jointly Optimizing Retrieval and Prediction for Multimodal Social Media Popularity
日本大学: 関与なし(対象大学)
- Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning
日本大学: 関与なし(対象大学)
- Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
日本大学: 関与なし(対象大学)
- Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection
日本大学: 関与なし(対象大学)
- Learning to Generate Structured Meshes with In-Context: Toward Generalization in Mesh Generation
日本大学: 関与なし(対象大学)
- Learning to Generate and Extract: A Multi-Agent Collaboration Framework for Zero-Shot Document-Level Event Arguments Extraction
日本大学: 関与なし(対象大学)
- Learning to LEAP: Efficient Dense Point Tracking by Focusing Where It Matters
日本大学: 関与なし(対象大学)
- Learning to Optimize Job Shop Scheduling Under Structural Uncertainty
日本大学: 関与なし(対象大学)
- Learning to Parse and Reconstruct: Bidirectional Modeling of Question-to-Program Mapping
日本大学: 関与なし(対象大学)
- Learning to Rank: How GNNs Solve Max-Clique and Sparse PCA
日本大学: 関与なし(対象大学)
- Learning to Tell Apart: Weakly Supervised Video Anomaly Detection via Disentangled Semantic Alignment
日本大学: 関与なし(対象大学)
- Learning with Preserving for Continual Multitask Learning
日本大学: 関与なし(対象大学)
- Learning with Structure: Computing Consistent Subsets on Structurally-Regular Graphs
日本大学: 関与なし(対象大学)
- Learning-Augmented Ski Rental with Discrete Distribution: A Bayesian Approach
日本大学: 関与なし(対象大学)
- Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction
日本大学: 関与なし(対象大学)
- Less Is Better: Sparse Instance Learning for Cross-Domain Few-Shot Object Detection
日本大学: 関与なし(対象大学)
- Less Is More: Rethinking Parameter-Efficient Fine-Tuning from a Subtractive Perspective
日本大学: 関与なし(対象大学)
- Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks
日本大学: 関与なし(対象大学)
- Less Is More: Vision Representation Compression for Efficient Video Generation with Large Language Models
日本大学: 関与なし(対象大学)
- Let the Model Learn to Feel: Mode-Guided Tonality Injection for Symbolic Music Emotion Recognition
日本大学: 関与なし(対象大学)
- Let the Void Be Void: Robust Open-Set Semi-Supervised Learning via Selective Non-Alignment
日本大学: 関与なし(対象大学)
- Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving
日本大学: 関与なし(対象大学)
- Let’s Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
日本大学: 関与なし(対象大学)
- Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels
日本大学: 関与なし(対象大学)
- Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection
日本大学: 関与なし(対象大学)
- Leveraging Image as Compressed Visual Prompt and Hierarchical Visual Knowledge for Effective Image Utilization in MLLMs
日本大学: 関与なし(対象大学)
- Leveraging Textual Compositional Reasoning for Robust Change Captioning
日本大学: 関与なし(対象大学)
- Leveraging Visual Blur Perception Characteristics for EEG Decoding
日本大学: 関与なし(対象大学)
- LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis
日本大学: 関与なし(対象大学)
- LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models
日本大学: 関与なし(対象大学)
- LiDAR-GS++: Improving LiDAR Gaussian Reconstruction via Diffusion Priors
日本大学: 関与なし(対象大学)
- LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
日本大学: 関与なし(対象大学)
- LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures
日本大学: 関与なし(対象大学)
- LiR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
日本大学: 関与なし(対象大学)
- LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
日本大学: 関与なし(対象大学)
- Libra-MIL: Multimodal Prototypes Stereoscopic Infused with Task-specific Language Priors for Few-shot Whole Slide Image Classification
日本大学: 関与なし(対象大学)
- LidarPainter: One-Step Away from Any Lidar View to Novel Guidance
日本大学: 関与なし(対象大学)
- LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
日本大学: 関与なし(対象大学)
- Lifelong Domain Adaptive 3D Human Pose Estimation
日本大学: 関与なし(対象大学)
- Lifelong Language-Conditioned Robotic Manipulation Learning
日本大学: 関与なし(対象大学)
- Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data
日本大学: 関与なし(対象大学)
- Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
日本大学: 関与なし(対象大学)
- Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation
日本大学: 関与なし(対象大学)
- Lightweight Adaptive Topological Layout and Semantic Mapping in Vision-and-Language Navigation on Websites
日本大学: 関与なし(対象大学)
- Lightweight Optimal-Transport Harmonization on Edge Devices
日本大学: 関与なし(対象大学)
- LinProVSR: Linguistics-Knowledge Guided Progressive Disambiguation Network for Visual Speech Recognition
日本大学: 関与なし(対象大学)
- Linear Time Algorithms for Individually Fair k-means via Multi-Swap Local Search
日本大学: 関与なし(対象大学)
- Listen like a Teacher: Mitigating Whisper Hallucinations Using Adaptive Layer Attention and Knowledge Distillation
日本大学: 関与なし(対象大学)
- Listening Between the Frames: Bridging Temporal Gaps in Large Audio-Language Models
日本大学: 関与なし(対象大学)
- LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence
日本大学: 関与なし(対象大学)
- LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs
日本大学: 関与なし(対象大学)
- LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers
日本大学: 関与なし(対象大学)
- LoGoSeg: Integrating Local and Global Features for Open-Vocabulary Semantic Segmentation
日本大学: 関与なし(対象大学)
- LoKI: Low-Damage Knowledge Implanting of Large Language Models
日本大学: 関与なし(対象大学)
- LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning
日本大学: 関与なし(対象大学)
- Local Guidance for Configuration-Based Multi-Agent Pathfinding
日本大学: 慶應義塾大学
- Localization-Anchored Instance Discrimination for Domain Adaptive Person Search
日本大学: 関与なし(対象大学)
- Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models
日本大学: 関与なし(対象大学)
- LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning
日本大学: 関与なし(対象大学)
- Logical Characterizations of GNNs with Mean Aggregation
日本大学: 関与なし(対象大学)
- Long-form RewardBench: Evaluating Reward Models for Long-form Generation
日本大学: 関与なし(対象大学)
- LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
日本大学: 関与なし(対象大学)
- LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images
日本大学: 関与なし(対象大学)
- LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations
日本大学: 関与なし(対象大学)
- Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs
日本大学: 関与なし(対象大学)
- Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
日本大学: 関与なし(対象大学)
- Look-Back: Implicit Visual Re-focusing in MLLM Reasoning
日本大学: 関与なし(対象大学)
- LookFlow: Training-Free and Efficient High-Resolution Image Synthesis via Dynamic Lookahead Guidance Flow
日本大学: 関与なし(対象大学)
- LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation
日本大学: 関与なし(対象大学)
- Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets
日本大学: 関与なし(対象大学)
- Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory
日本大学: 関与なし(対象大学)
- Lost in Time? A Meta-Learning Framework for Time-Shift-Tolerant Physiological Signal Transformation
日本大学: 関与なし(対象大学)
- Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-tuning
日本大学: 関与なし(対象大学)
- LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules
日本大学: 関与なし(対象大学)
- M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data
日本大学: 関与なし(対象大学)
- M2FMoE: Multi-Resolution Multi-View Frequency Mixture-of-Experts for Extreme-Adaptive Time Series Forecasting
日本大学: 関与なし(対象大学)
- M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference
日本大学: 関与なし(対象大学)
- M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction
日本大学: 関与なし(対象大学)
- M3Time: LLM-Enhanced Multi-Modal, Multi-Scale, and Multi-Frequency Multivariate Time Series Forecasting
日本大学: 関与なし(対象大学)
- M3UCD: A Multi-task Multimodal Metaphor Understanding Challenge Dataset for LLMs
日本大学: 関与なし(対象大学)
- M3ashy: Multi-Modal Material Synthesis via Hyperdiffusion
日本大学: 関与なし(対象大学)
- MACRec: A Multi-View Subspace Alignment Framework for Contrastive Sampling Calibration in Recommendation
日本大学: 関与なし(対象大学)
- MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment
日本大学: 関与なし(対象大学)
- MACoT: Synthesizing Chains of Thought for Small Models via Multi-Agent Collaboration
日本大学: 関与なし(対象大学)
- MAGIC: Mastering Physical Adversarial Generation in Context Through Collaborative LLM Agents
日本大学: 東京大学
- MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss
日本大学: 関与なし(対象大学)