KAIST AI

KAIST AI on Hugging Face Daily Papers: 107 papers, 12 in the top 3 of their day, 5 paper of the day.

  1. Out of Sight, Still in Mind: Token Compression for Omni-LLMs 0 upvotes, #20 of 2026-11-19
  2. eDIAR: Training-Free Open-Speaker Streaming Diarization for Long Meetings and Large Archives via e-means 3 upvotes, #30 of 2026-11-16
  3. Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents 69 upvotes, #1 of 2026-11-11
  4. Future Representation Distillation for Imagination-free World Action Models 12 upvotes, #16 of 2026-11-06
  5. Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs 15 upvotes, #17 of 2026-11-05
  6. DreamX: Video Diffusion Model is a Universal Latent Action Learner 56 upvotes, #6 of 2026-11-04
  7. Factorized MLLM Embeddings for Composed Image Retrieval 47 upvotes, #9 of 2026-11-04
  8. RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On 14 upvotes, #23 of 2026-11-04
  9. Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay 35 upvotes, #10 of 2026-11-03
  10. Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling 2 upvotes, #34 of 2026-11-02
  11. Latent Reasoning in Continuous Space for Unified Multimodal Models 45 upvotes, #3 of 2026-11-02
  12. Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs 116 upvotes, #1 of 2026-10-30
  13. L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory 47 upvotes, #4 of 2026-10-30
  14. OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images 58 upvotes, #1 of 2026-10-29
  15. Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data 17 upvotes, #19 of 2026-10-28
  16. Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery 25 upvotes, #11 of 2026-10-27
  17. Self-Distilling Future Video Representations for World Action Models 52 upvotes, #10 of 2026-10-23
  18. KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization 49 upvotes, #13 of 2026-10-15
  19. Latent World Action Model for GUI Agents 26 upvotes, #44 of 2026-10-14
  20. Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction 70 upvotes, #7 of 2026-10-09
  21. FastOPD: On-Policy Distillation for Lightweight VLA Deployment 2 upvotes, #62 of 2026-10-08
  22. GRACE: Generation-aware latent compression for efficient video generation 88 upvotes, #6 of 2026-10-08
  23. Q-Learning with Scalar Adjoint Matching 25 upvotes, #31 of 2026-10-08
  24. LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation 1 upvotes, #69 of 2026-10-08
  25. RunningTab: Direct Workspace Interaction with Environment-Side Tabs 40 upvotes, #18 of 2026-10-08
  26. Tetris3D: 3D Scene Generation With Objects That Fit Together 48 upvotes, #14 of 2026-10-08
  27. Harness-Aware Distillation for Small Language Model Agents 16 upvotes, #34 of 2026-10-07
  28. RobotUse: Allocating Computation, Context, and Decisions 19 upvotes, #30 of 2026-10-06
  29. Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models 13 upvotes, #55 of 2026-10-02
  30. World Observer: Joint Actor-Observer Generation for Persistent World Modeling 87 upvotes, #10 of 2026-10-02
  31. Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering 72 upvotes, #13 of 2026-10-01
  32. Overcoming Scaling Limits in On-Policy Self-Distillation for LLM Reasoning 8 upvotes, #50 of 2026-10-01
  33. Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR 63 upvotes, #19 of 2026-09-30
  34. Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge 41 upvotes, #17 of 2026-09-29
  35. Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning 46 upvotes, #14 of 2026-09-29
  36. EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents 39 upvotes, #9 of 2026-09-17
  37. PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization 27 upvotes, #10 of 2026-09-14
  38. SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem 137 upvotes, #3 of 2026-09-11
  39. Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation 94 upvotes, #4 of 2026-09-09
  40. Language Models Can Control Their Own Attention 68 upvotes, #7 of 2026-09-03
  41. Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase 27 upvotes, #13 of 2026-09-01
  42. J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data 43 upvotes, #6 of 2026-08-31
  43. PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents 9 upvotes, #18 of 2026-08-21
  44. MBA: Multimodal Benchmark and Agents for Real-World Business Ideation 6 upvotes, #16 of 2026-08-13
  45. Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory 49 upvotes, #7 of 2026-08-11
  46. ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition 65 upvotes, #4 of 2026-07-29
  47. See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models 7 upvotes, #21 of 2026-07-20
  48. LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL 32 upvotes, #8 of 2026-07-08
  49. 3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance 7 upvotes, #25 of 2026-07-08
  50. PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents 8 upvotes, #27 of 2026-06-30
  51. MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation 35 upvotes, #7 of 2026-06-25
  52. Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views 5 upvotes, #33 of 2026-06-23
  53. TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs 30 upvotes, #8 of 2026-06-17
  54. Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models 33 upvotes, #7 of 2026-06-16
  55. Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization 33 upvotes, #11 of 2026-06-10
  56. Trust Region Q Adjoint Matching 3 upvotes, #34 of 2026-06-05
  57. TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration 44 upvotes, #3 of 2026-06-05
  58. Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling 5 upvotes, #32 of 2026-06-03
  59. Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases 7 upvotes, #48 of 2026-05-29
  60. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources 76 upvotes, #3 of 2026-05-29
  61. Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents 38 upvotes, #10 of 2026-05-28
  62. Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction 41 upvotes, #5 of 2026-05-27
  63. HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents 11 upvotes, #18 of 2026-05-25
  64. FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching 29 upvotes, #14 of 2026-05-22
  65. WorldKV: Efficient World Memory with World Retrieval and Compression 41 upvotes, #10 of 2026-05-22
  66. It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs 30 upvotes, #10 of 2026-05-21
  67. Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR 33 upvotes, #11 of 2026-05-18
  68. PREPING: Building Agent Memory without Tasks 28 upvotes, #13 of 2026-05-15
  69. MEME: Multi-entity & Evolving Memory Evaluation 7 upvotes, #36 of 2026-05-13
  70. CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models 68 upvotes, #3 of 2026-05-12
  71. Towards Autonomous Mechanistic Reasoning in Virtual Cells 6 upvotes, #20 of 2026-04-17
  72. Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents 29 upvotes, #5 of 2026-04-16
  73. Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models 35 upvotes, #5 of 2026-03-30
  74. Representation Alignment for Just Image Transformers is not Easier than You Think 13 upvotes, #11 of 2026-03-27
  75. T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search 36 upvotes, #5 of 2026-03-26
  76. DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models 50 upvotes, #5 of 2026-03-25
  77. Repurposing Geometric Foundation Models for Multi-view Diffusion 45 upvotes, #7 of 2026-03-24
  78. RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models 23 upvotes, #14 of 2026-03-24
  79. SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection 3 upvotes, #31 of 2026-03-24
  80. SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning 45 upvotes, #7 of 2026-03-24
  81. ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation 1 upvotes, #42 of 2026-03-18
  82. MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents 28 upvotes, #6 of 2026-03-12
  83. Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams 17 upvotes, #9 of 2026-03-12
  84. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models 54 upvotes, #1 of 2026-02-26
  85. RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning 10 upvotes, #11 of 2026-02-24
  86. THINKSAFE: Self-Generated Safety Alignment for Reasoning Models 38 upvotes, #5 of 2026-02-02
  87. Lost in the Noise: How Reasoning Models Fail with Contextual Distractors 29 upvotes, #6 of 2026-01-13
  88. InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion 95 upvotes, #2 of 2025-12-29
  89. Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation 27 upvotes, #6 of 2025-12-23
  90. Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure 28 upvotes, #7 of 2025-12-17
  91. Directional Textual Inversion for Personalized Text-to-Image Generation 2 upvotes, #34 of 2025-12-16
  92. EgoX: Egocentric Video Generation from a Single Exocentric Video 106 upvotes, #1 of 2025-12-15
  93. Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models 7 upvotes, #26 of 2025-12-05
  94. Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset 25 upvotes, #5 of 2025-11-20
  95. KLASS: KL-Guided Fast Inference in Masked Diffusion Models 35 upvotes, #3 of 2025-11-12
  96. When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling 32 upvotes, #7 of 2025-10-21
  97. Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models 29 upvotes, #11 of 2025-10-15
  98. Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs 46 upvotes, #5 of 2025-10-13
  99. Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning 54 upvotes, #7 of 2025-10-10
  100. Verifier-free Test-Time Sampling for Vision Language Action Models 2 upvotes, #34 of 2025-10-08

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.