Jiayi Chen
収録論文 37本 ・ フィジカルAI/ロボット学習
VLAワールドモデル
※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
- 4D-WAM: 軌跡フィールドによる世界行動モデルへの時空間認識の注入VLA2026/8/8
ロボットの行動生成と動画予測を統合する世界行動モデルに、3次元軌跡フィールドの時空間知識を表現整合で注入する訓練戦略を提案し、空間理解と実行精度を向上させた。
- 4D-WAM: 軌跡フィールドによる世界行動モデルへの時空間認識の注入VLA2026/8/8
ロボットの行動生成と動画予測を統合する世界行動モデルに、3次元軌跡フィールドの時空間知識を表現整合で注入する訓練戦略を提案。局所的な動き整合と長期的な目的地整合の2つの目的関数により、軌跡レベルの時空間表現を学習し、空間理解や実行精度、汎化性を向上させる。
- 前方予測だけで十分か？JEPAワールドモデルのための物理状態接地ワールドモデル2026/8/7
JEPAベースのワールドモデルに、ロボットの自己受容状態と関節角変化を接地する2つの目的を追加し、潜在表現の識別性と下流タスク性能を向上させる手法を提案した。
- Is Forward Prediction Enough? Physical State Grounding for JEPA World Models2026/8/1
- 4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields2026/8/1
- KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation2026/6/1
- RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark2026/5/1
- Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning2026/4/1
- BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes2026/4/1
- GraspADMM: Improving Dexterous Grasp Synthesis via ADMM Optimization2026/3/1
- Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning2026/3/1
- Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance2026/3/1
- TacDexGrasp: Compliant and Robust Dexterous Grasping with Tactile Feedback2026/3/1
- DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching2026/3/1
- Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline2026/2/1
- LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion2026/2/1
- Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives2025/12/1
- Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process2025/11/1
- Robust Differentiable Collision Detection for General Objects2025/11/1
- Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey2025/10/1
- FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Models2025/8/1
- ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver2025/8/1
- DexVLG: Dexterous Vision-Language-Grasp Model at Scale2025/7/1
- RationalVLA: A Rational Vision-Language-Action Model with Dual System2025/6/1
- CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding2025/6/1
- GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data2025/5/1
- Dexonomy: Synthesizing All Dexterous Grasp Types in a Grasp Taxonomy2025/4/1
- Opportunistic Collaborative Planning with Large Vision Model Guided Control and Joint Query-Service Optimization2025/4/1
- PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding2025/3/1
- BODex: Scalable and Efficient Robotic Dexterous Grasp Synthesis Using Bilevel Optimization2024/12/1
- RoboHanger: Learning Generalizable Robotic Hanger Insertion for Diverse Garments2024/12/1
- DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes2024/10/1
- D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation2024/9/1
- Task-Oriented Dexterous Hand Pose Synthesis Using Differentiable Grasp Wrench Boundary Estimator2023/9/1
- UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy2023/3/1
- PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations2023/3/1
- DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation2022/10/1