← 人才雷達人才雷达 · Talent Radar
STAGE 04 · 03

實驗室 实验室

Labs

65 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。

65 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 · 65

Shanghai Jiao Tong University

90d 12 7d 1 Last: 2026-08-01 (86d)
研究焦點：研究焦点： Flow MatchingDiffusion Policy
近期 ⚡/🔧近期 ⚡/🔧 FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulation 2026-08-01 Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference 2026-08-07 Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control 2026-08-08

Tsinghua University

90d 7 7d 0 Last: 2026-07-29 (89d)
研究焦點：研究焦点： Flow MatchingDexterous Manipulation
近期 ⚡/🔧近期 ⚡/🔧 XS-VLA: Coupling Coarse-grained Spatial Distillation with Latent Flow Matching for Lightweight Robotic Control 2026-07-29 Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies 2026-08-11 PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies 2026-08-19

The Hong Kong University of Science and Technology (Guangzhou)

師徒 →
90d 6 7d 0 Last: 2026-08-08 (79d)
研究焦點：研究焦点： Cross-Embodiment Foundation ModelsFlow Matching
近期 ⚡/🔧近期 ⚡/🔧 DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation 2026-08-08 DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching 2026-08-08 DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation 2026-08-09

University of Science and Technology of China

師徒 →
90d 5 7d 0 Last: 2026-09-08 (48d)
近期 ⚡/🔧近期 ⚡/🔧 VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models 2026-09-08 VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models 2026-09-09 VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models 2026-09-11

Institute for AI Industry Research (AIR), Tsinghua University

90d 5 7d 0 Last: 2026-08-07 (80d)
研究焦點：研究焦点： Mobile ManipulationTactile Sensing
近期 ⚡/🔧近期 ⚡/🔧 MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight 2026-08-07 MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight 2026-08-08 MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight 2026-08-09

Harbin Institute of Technology

師徒 →
90d 5 7d 0 Last: 2026-08-14 (73d)
近期 ⚡/🔧近期 ⚡/🔧 RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models 2026-08-14 EATR-Stereo: Embodiment-Aware Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Control 2026-08-20 EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Control 2026-08-21

Huazhong University of Science and Technology

師徒 →
90d 3 7d 0 Last: 2026-07-31 (87d)
研究焦點：研究焦点： Action Tokenization
近期 ⚡/🔧近期 ⚡/🔧 TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM 2026-07-31 LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models 2026-08-20 ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models 2026-09-18

The Hong Kong University of Science and Technology

90d 3 7d 0 Last: 2026-08-01 (86d)
研究焦點：研究焦点： VLA Generalist
近期 ⚡/🔧近期 ⚡/🔧 RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy 2026-08-01 World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation 2026-08-08 World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation 2026-08-09

清华

師徒 →
90d 3 7d 0 Last: 2026-09-22 (34d)
研究焦點：研究焦点： Inverse Dynamics ModelsCross-Embodiment Foundation Models
近期 ⚡/🔧近期 ⚡/🔧 GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments 2026-09-22 LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos 2026-10-13 LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos 2026-10-14

AI App · 1