STAGE 04 · 03

實驗室实验室

Labs

24 個實驗室 在 90 天滾動窗口中有 ≥2 條信號，按信號數排序；14 日走勢圖顯示每日活躍度。

24 个实验室 在 90 天滚动窗口中有 ≥2 条信号，按信号数排序；14 日走势图显示每日活跃度。

VLA · 24

NVIDIA

Practical

90d 16 7d 0 Last: 2026-03-13 (89d)

研究焦點：研究焦点： Computer Use (Desktop)Frontier Models

近期 ⚡/🔧近期 ⚡/🔧 Practical Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling 2026-03-13 Practical VideoWeaver: Multimodal Multi-View Video-to-Video Transfer for Embodied Agents 2026-03-27 Practical Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient 2026-05-28

清华

師徒 → Breakthrough

90d 13 7d 0 Last: 2026-03-13 (89d)

研究焦點：研究焦点： Dexterous ManipulationInverse Dynamics ModelsRobot Safety

近期 ⚡/🔧近期 ⚡/🔧 Practical Seeing Space and Motion: Enhancing Latent Actions with Geometric and Dynamic Awareness for Vision-Language-Action Models 2026-03-13 Practical FG-CLTP: Fine-Grained Contrastive Language Tactile Pretraining for Robotic Manipulation 2026-03-13 Breakthrough Fast-WAM: Do World Action Models Need Test-time Future Imagination? 2026-03-19

CMU

師徒 → Breakthrough

90d 5 7d 0 Last: 2026-03-12 (90d)

研究焦點：研究焦点： Video Generation for Robotics

近期 ⚡/🔧近期 ⚡/🔧 Practical ViPRA: Video Prediction for Robot Actions 2026-04-01 Practical RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild 2026-04-10 Breakthrough HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy 2026-04-17

Berkeley

Practical

90d 5 7d 0 Last: 2026-03-13 (89d)

研究焦點：研究焦点： Agentic CodingImitation LearningCross-Embodiment Foundation Models

近期 ⚡/🔧近期 ⚡/🔧 Practical Cross-Hand Latent Representation for Vision-Language-Action Models 2026-03-13 Practical Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning 2026-04-02 Practical X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations 2026-04-17

ETH

Practical

90d 4 7d 0 Last: 2026-03-13 (89d)

研究焦點：研究焦点： Autoregressive ActionCross-Embodiment Foundation Models

近期 ⚡/🔧近期 ⚡/🔧 Practical Update-Free On-Policy Steering via Verifiers 2026-03-13 Practical AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models 2026-03-13 Practical Latent Action Diffusion for Cross-Embodiment Manipulation 2026-03-24

DeepMind

Practical

90d 4 7d 0 Last: 2026-03-13 (89d)

近期 ⚡/🔧近期 ⚡/🔧 Practical Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation 2026-03-19

浙大

師徒 → Practical

90d 3 7d 0 Last: 2026-03-13 (89d)

研究焦點：研究焦点： Dexterous Manipulation

近期 ⚡/🔧近期 ⚡/🔧 Practical AdaClearGrasp: Learning Adaptive Clearing for Zero-Shot Robust Dexterous Grasping in Densely Cluttered Environments 2026-03-13 Practical FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model 2026-03-13 Practical Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models 2026-03-19

Microsoft

Breakthrough

90d 3 7d 0 Last: 2026-04-28 (43d)

近期 ⚡/🔧近期 ⚡/🔧 Breakthrough MolmoAct2: Action Reasoning Models for Real-world Deployment 2026-05-12

Princeton

Practical

90d 3 7d 0 Last: 2026-03-13 (89d)

研究焦點：研究焦点： Diffusion Policy

近期 ⚡/🔧近期 ⚡/🔧 Practical PPGuide: Steering Diffusion Policies with Performance Predictive Guidance 2026-03-13 Practical Contact-Rich Robotic Assembly in Construction via Diffusion Policy Learning 2026-04-22

LIBERO Team

Practical

90d 3 7d 0 Last: 2026-05-27

近期 ⚡/🔧近期 ⚡/🔧 Practical LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization 2026-05-27 Practical Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models 2026-05-28 Practical What Frozen VLAs Already Know About Success: A Probing Study of Value-Like Structure in Foundation Robot Policies 2026-05-29

Stanford

師徒 → Practical

90d 2 7d 0 Last: 2026-03-20 (82d)

近期 ⚡/🔧近期 ⚡/🔧 Practical UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception 2026-04-17