Di Zhang

Tongji University

収録論文 12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

• GWM-VLA：視覚言語行動学習のための幾何認識潜在世界モデリング
  VLA2026/8/7

  視覚言語行動モデルの堅牢性を向上させるため、多視点の幾何関係を明示的にモデル化する潜在世界モデルを提案し、シミュレーションと実環境で性能を検証した。

• GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning
  2026/8/1
• HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
  2026/7/28
• HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
  2026/7/1
• PhysInOne: Visual Physics Learning and Reasoning in One Suite
  2026/4/1
• Learning Native Continuation for Action Chunking Flow Policies
  2026/2/1
• Learning Geometrically-Grounded 3D Visual Representations for View-Generalizable Robotic Manipulation
  2026/1/1
• Point What You Mean: Visually Grounded Instruction Policy
  2025/12/1
• Do You Need Proprioceptive States in Visuomotor Policies?
  2025/9/1
• KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation
  2025/5/1
• SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain
  2025/3/1
• Focus On What Matters: Separated Models For Visual-Based RL Generalization
  2024/10/1