HotPaper.ai — 매일 자동 큐레이션되는 AI 논문 Top 25 + 한국어 요약

1. #1Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?

2. #2VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

3. #3The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset

4. #4Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

5. #5AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding

6. #6ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?

7. #7TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

8. #8AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints

9. #9Flash-WAM: Modality-Aware Distillation for World Action Models

10. #10RobotValues: Evaluating Household Robots When Human Values Conflict

11. #11Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

12. #12LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing

13. #13Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

14. #14Personal AI Agent for Camera Roll VQA

15. #15Complexity-Balanced Diffusion Splitting

16. #16MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

    Shangheng Du, Xiangchao Yan, Jinxin Shi, Zongsheng Cao, Shiyang Feng

17. #17Unsupervised Skill Discovery for Agentic Data Analysis

18. #18Quality-Guided Semi-Supervised Learning for Medical Image Segmentation

19. #19MAOAM: Unified Object and Material Selection with Vision-Language Models

20. #20LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

21. #21The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs

22. #22World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis

23. #23OPRD: On-Policy Representation Distillation

24. #24Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

25. #25Latent Reasoning with Normalizing Flows

인기 키워드

reinforcement-learning (225) llm (139) diffusion-models (116) llm-agents (109) vlm (98) transformer (82) llm-evaluation (77) video-generation (68) long-context (55) benchmark-evaluation (53) retrieval-augmented (50) vision-language (50) code-generation (49) flow-matching (48) long-horizon (47) text-to-image (46) large-language-models (44) mllm (44) fine-tuning (41) foundation-models (41)