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

2026-09-25 featured 논문 30편

  1. #1HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation

    Yi Li, Yuquan Deng, Jesse Zhang, J. Jang, Marius Memmel

  2. #2Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making

    Embodied Agent Interface를 통해 LLM의 몸체화 결정 과제 성능을 체계적으로 평가하고, 핵심 모듈별 오류를 분석하여 활용 방향을 제시한다.

    Manling Li, Shiyu Zhao, Qineng Wang, Kangrui Wang, Yu Zhou

  3. #3Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

    Ovis-Embedding은 텍스트, 이미지, 영상, 오디오를 통합한 공통 임베딩 공간을 생성하는 최신 옴니모달 임베딩 모델이다.

    Ovis-Embedding Team

  4. #4InternW0: A Foundational Physical World Model for Efficient Real-World Interactions

  5. #5Transformers without Normalization

    Jiacheng Zhu, Xinlei Chen, Kaiming He, Yann LeCun, Zhuang Liu

  6. #6WonderWorld: Interactive 3D Scene Generation from a Single Image

    Hong-Xing Yu, Haoyi Duan, Charles Herrmann, William T. Freeman, Jiajun Wu

  7. #7GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

    Sreyan Ghosh, Sonal Kumar, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi

  8. #8Quantifying the Persona Effect in LLM Simulations

    Tiancheng Hu, Nigel Collier

  9. #9In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

    Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, Yi Yang

  10. #10Taming Rectified Flow for Inversion and Editing

    RF-Solver와 RF-Edit을 제안하여, Rectified Flow 기반 모델의 인버전 정확도와 편집 성능을 훈련 없이 향상시킨다.

    Jiangshan Wang, Junfu Pu, Zhongang Qi, J. Guo, Yue Ma

  11. #11Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

    Haocheng Xi, Shuo Yang, Yilong Zhao, Chenfeng Xu, Muyang Li

  12. #12Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

    Junyu Chen, Han Cai, Junsong Chen, Enze Xie, Shang Yang

  13. #41Embedding Physics Priors in Robot Learning: A Survey

    로봇 학습에 물리학 사전지식을 통합하는 방법을 체계적으로 분류하고, 주요 응용 분야와 개방적 문제를 조망한 서베이 논문.

    Mattia Piccinini, Lucas Schulze, Alice Plebe, Matteo Saveriano, Thomas Beckers

  14. #297Lean Pool: An AI-Maintained Archive of Formalized Mathematics

    Lean Pool은 AI 에이전트가 관리하는 형식화 수학 아카이브 시스템이다.

    Vasily Ilin

  15. #305HappyWorld-Bench

  16. #306JEV-as-a-Judge: Accept When Confident, Escalate When Unsure

    JEV-as-a-Judge는 저비용으로 신뢰도 높은 판단을 제공하며, 불확실한 경우에만 강력한 모델로 전달하는 방식으로 99%의 정확도를 유지한다.

    Yubo Li, Yidi Miao, Ramayya Krishnan, Rema Padman

  17. #307The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

    Taste-Bench라는 새로운 벤치마크를 제안하여 LLM 에이전트의 장기적 판단력(‘taste’)을 측정하고 훈련한다.

    Wenbo Pan, Zhichao Liu, Shujie Liu, Jingying Zeng, Chin-Yew Lin

  18. #308SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

  19. #309Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI

  20. #310PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

  21. #311MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

  22. #312Do Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation

    Upworthy A/B 테스트 데이터를 기반으로, 인공 인물(persona)을 사용한 마케팅 콘텐츠 시뮬레이션은 예측 정확도가 낮아, 단순 LLM 기반 순위 매기기가 더 효과적임을 밝힘.

    Alexandre Cristovão Maiorano

  23. #313X-Planner: Event-Structured Task Planning for Embodied Intelligence

  24. #314Hunyuan-A13B Technical Report

  25. #315Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

  26. #316GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

    GAE는 3D 일관성 있는 세계 생성을 위한 기하학적 인코딩을 갖춘 압축된 잠재 공간을 학습하여 생성 및 인식 간의 공유 인터페이스를 제시한다.

    Jiahao Lu, Minghao Yin, Wenbo Hu, Hengyu Liu, Wang Zhao

  27. #317All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

  28. #318The Past Frames the Future: Memory for Autoregressive Video Generation

  29. #319Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

  30. #320Bellman Policy Optimization

인기 키워드

reinforcement-learning (374) diffusion-models (216) llm (212) llm-agents (173) video-generation (149) llm-evaluation (147) transformer (140) vision-language (136) large-language-models (119) long-context (113) vlm (110) code-generation (102) long-horizon (98) benchmark-evaluation (97) benchmarking (91) language-models (90) foundation-models (80) retrieval-augmented (80) world-models (75) flow-matching (73)