VLA
VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
Zhide Zhong et al. · VLA 后训练范式（SFT+RL 桥接），有明确部署应用路径
cs.RO
閱讀原文
VLA 研究日報 Pulsar
LIVE
— AI 線今日無資料 —— AI 线今日无资料 —
VLA 線VLA 线 · cs.RO · cs.AI · cs.LG
- MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model Quan Dao et al. · 通用扩散架构改进，无明确 VLA 应用路径 CS.CV
- Shared Representation for 3D Pose Estimation, Action Classification, and Progress Prediction from Tactile Signals Isaac Han et al. · 触觉感知但聚焦人体姿态估计，非机器人操作 VLA CS.CV
- Addressing Ambiguity in Imitation Learning through Product of Experts based Negative Feedback John Bateman et al. · 传统模仿学习方法，无 VLA 架构关联 CS.RO
- BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments Yuxuan Li et al. · 安全基准但侧重数字代理，物理机器人实验不明确 CS.AI
- Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI Xinhao Liu et al. · 具身导航仿真平台，填补仿真底座方向但非 VLA 算法 CS.RO
- Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting Haichao Zhang et al. · 轨迹预测任务，VLA 相邻但非控制策略 CS.RO
- CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning Jiange Yang et al. · 视频潜运动学习用于机器人，无明确 VLA 架构 CS.RO
- SOMA: Strategic Orchestration and Memory-Augmented System for Vision-Language-Action Model Robustness via In-Context Adaptation Zhuoran Li et al. · VLA 鲁棒性方法，标题宏大但贡献细节不足 [💧灌水] CS.RO
- VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation Zhide Zhong et al. · VLA 后训练范式（SFT+RL 桥接），有明确部署应用路径 CS.RO
- Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning Xinqi et al. · 开源灵巧手硬件，重要资源但非 VLA 算法 CS.RO
- T-800: An 800 Hz Data Glove for Precise Hand Gesture Tracking Haoyang Luo et al. · 高频数据手套硬件，传感设备非 VLA 方法 CS.RO
- Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate Chen Yang et al. · VLA 部署效率优化 V2，解决真实部署速度问题 CS.RO
VLA 研究日報VLA 研究日报
共 17 篇
🔧 技術技术
VLA
Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
Chen Yang et al. · VLA 部署效率优化 V2，解决真实部署速度问题
cs.RO
閱讀原文
VLA
DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching
Jiayi Chen et al. · VLA 动作解码改进（离散流匹配），有实质架构贡献
cs.RO
閱讀原文
📖 背景閱讀背景阅读
VLA
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
Quan Dao et al. · 通用扩散架构改进，无明确 VLA 应用路径
cs.CV
閱讀原文
VLA
Shared Representation for 3D Pose Estimation, Action Classification, and Progress Prediction from Tactile Signals
Isaac Han et al. · 触觉感知但聚焦人体姿态估计，非机器人操作 VLA
cs.CV
閱讀原文
VLA
Addressing Ambiguity in Imitation Learning through Product of Experts based Negative Feedback
John Bateman et al. · 传统模仿学习方法，无 VLA 架构关联
cs.RO
閱讀原文
VLA
BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
Yuxuan Li et al. · 安全基准但侧重数字代理，物理机器人实验不明确
cs.AI
閱讀原文
VLA
Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
Xinhao Liu et al. · 具身导航仿真平台，填补仿真底座方向但非 VLA 算法
cs.RO
閱讀原文
VLA
Out-of-Sight Embodied Agents: Multimodal Tracking, Sensor Fusion, and Trajectory Forecasting
Haichao Zhang et al. · 轨迹预测任务，VLA 相邻但非控制策略
cs.RO
閱讀原文
VLA
CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning
Jiange Yang et al. · 视频潜运动学习用于机器人，无明确 VLA 架构
cs.RO
閱讀原文
VLA
SOMA: Strategic Orchestration and Memory-Augmented System for Vision-Language-Action Model Robustness via In-Context Adaptation
Zhuoran Li et al. · VLA 鲁棒性方法，标题宏大但贡献细节不足 [💧灌水]
cs.RO
閱讀原文
VLA
Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning
Xinqi et al. · 开源灵巧手硬件，重要资源但非 VLA 算法
cs.RO
閱讀原文
VLA
T-800: An 800 Hz Data Glove for Precise Hand Gesture Tracking
Haoyang Luo et al. · 高频数据手套硬件，传感设备非 VLA 方法
cs.RO
閱讀原文
VLA
DiffusionAnything: End-to-End In-context Diffusion Learning for Unified Navigation and Pre-Grasp Motion
Iana Zhura et al. · 扩散策略用于导航 + 预抓取，VLA 相邻但架构创新一般
cs.RO
閱讀原文
VLA
Policy-Guided World Model Planning for Language-Conditioned Visual Navigation
Amirhosein Chahe et al. · 语言条件导航，世界模型 + 策略但非操作 VLA
cs.RO
閱讀原文
VLA
Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
Yiyuan Pan et al. · 长视野任务神经符号方法，VLA 相邻但无明确架构
cs.RO
閱讀原文
VLA
ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models
Yiru Wang et al. · VLA 效率方法但聚焦自动驾驶，按标准降级
cs.RO
閱讀原文