Jianan Wang

Astribot

収録論文 15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

• 視覚言語行動モデルをオンザフライツール使用エージェントへ進化させる
  VLA/ツール使用2026/8/14

  VLAモデルにツール注入フレームワークを統合し、低次視覚・高次アフォーダンス・身体性を強化するエージェントARTを提案。ツール使用により行動解空間を縮小し、汎用性向上とデータ依存低減を実現。

• A Glimpse into Long-term Physical Coexistence with Intelligent Robots
  2026/7/1
• PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation
  2026/7/1
• Towards Predictive, Aligned, and Scalable Robot Learning
  2026/7/1
• When to Trust Imagination: Adaptive Action Execution for World Action Models
  2026/5/1
• StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
  2026/5/1
• LogicEnvGen: Task-Logic Driven Generation of Diverse Simulated Environments for Embodied AI
  2026/1/1
• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
  2026/1/1
• Mind to Hand: Purposeful Robotic Control via Embodied Reasoning
  2025/12/1
• SimTac: A Physics-Based Simulator for Vision-Based Tactile Sensing with Biomorphic Structures
  2025/11/1
• DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation
  2025/9/1
• Towards Human-level Intelligence via Human-like Whole-Body Manipulation
  2025/7/1
• ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
  2025/6/1
• BeSimulator: A Large Language Model Powered Text-based Behavior Simulator
  2024/9/1
• Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
  2019/6/1