Unnat Jain

収録論文 17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

• 統一視覚運動ターゲット：物理的行動を超えたVLAの教師信号
  VLA2026/8/4

  VLAモデルの予測ターゲットを、モーター制御と視覚シーン遷移を統合した潜在表現に変更し、アーキテクチャ変更なしで学習効率と性能を向上させる手法を提案した。

• Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actions
  2026/8/1
• Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
  2026/7/1
• DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning
  2026/7/1
• CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance
  2026/3/1
• ViPRA: Video Prediction for Robot Actions
  2025/11/1
• Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
  2025/7/1
• Exploitation-Guided Exploration for Semantic Embodied Navigation
  2023/11/1
• Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
  2023/10/1
• An Unbiased Look at Datasets for Visuo-Motor Pre-Training
  2023/10/1
• Adaptive Coordination in Social Embodied Rearrangement
  2023/6/1
• MOPA: Modular Object Navigation with PointGoal Agents
  2023/4/1
• Affordances from Human Videos as a Versatile Representation for Robotics
  2023/4/1
• Last-Mile Embodied Visual Navigation
  2022/11/1
• Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments
  2021/9/1
• MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
  2020/12/1
• AllenAct: A Framework for Embodied AI Research
  2020/8/1