Yonatan Bisk

Carnegie Mellon University

収録論文 41本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• 再構築の迷子：視覚-言語-行動モデルにおける行動表現と言語の整合
  VLA/行動表現2026/8/11

  行動軌跡には言語的意味情報が含まれるが、再構築のみのトークン化で失われるため、凍結VLMで指示を復元する補助損失を持つセマンティック整合トークナイザSALTを提案し、言語条件付き制御の成功率を大幅に向上させた。

• Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models
  2026/8/1
• Inductive Generalization for Robotic Manipulation
  2026/6/19
• ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies
  2026/6/1
• Inductive Generalization for Robotic Manipulation
  2026/6/1
• Flatness Preserves Instruction Following in Vision-Language-Action Models
  2026/6/1
• IndoorR2X: Indoor Robot-to-Everything Coordination with LLM-Driven Planning
  2026/3/1
• Affordance RAG: Hierarchical Multimodal Retrieval with Affordance-Aware Embodied Memory for Mobile Manipulation
  2025/12/1
• RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
  2025/10/27
• RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
  2025/10/1
• High Torque Density PCB Axial Flux Permanent Magnet Motor for Micro Robots
  2025/9/1
• RAVEN: Resilient Aerial Navigation via Open-Set Semantic Memory and Behavior Adaptation
  2025/9/1
• Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models
  2025/6/1
• ANAVI: Audio Noise Awareness using Visuals of Indoor environments for NAVIgation
  2024/10/1
• MotIF: Motion Instruction Fine-tuning
  2024/9/1
• Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
  2024/9/1
• DegustaBot: Zero-Shot Visual Preference Estimation for Personalized Multi-Object Rearrangement
  2024/7/1
• Situated Instruction Following
  2024/7/1
• Towards Open-World Mobile Manipulation in Homes: Lessons from the Neurips 2023 HomeRobot Open Vocabulary Mobile Manipulation Challenge
  2024/7/1
• Dialogue with Robots: Proposals for Broadening Participation and Research in the SLIVAR Community
  2024/4/1
• Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers
  2024/3/1
• Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis
  2023/12/1
• Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation
  2023/12/1
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
  2023/10/1
• MOSAIC: Learning Unified Multi-Sensory Object Property Representations for Robot Learning via Interactive Perception
  2023/9/1
• Reasoning about the Unseen for Efficient Outdoor Object Navigation
  2023/9/1
• MAEA: Multimodal Attribution for Embodied AI
  2023/7/1
• HomeRobot: Open-Vocabulary Mobile Manipulation
  2023/6/1
• Spatial-Language Attention Policies for Efficient Robot Learning
  2023/4/1
• Self-Supervised Object Goal Navigation with In-Situ Finetuning
  2022/12/1
• Transformers are Adaptable Task Planners
  2022/7/1
• A Framework for Learning to Request Rich and Contextually Useful Information from Humans
  2021/10/1
• Language Grounding with 3D Objects
  2021/7/1
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
  2020/10/1
• RMM: A Recursive Mental Model for Dialog Navigation
  2020/5/1
• ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
  2019/12/1
• Improving Robot Success Detection using Static Object Data
  2019/4/1
• Prospection: Interpretable Plans From Language By Predicting the Future
  2019/3/1
• Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation
  2019/3/1
• Early Fusion for Goal Directed Robotic Vision
  2018/11/1
• Balancing Shared Autonomy with Human-Robot Communication
  2018/5/1