Search

7 results for “LIBERO”

1. Research · Robotics & embodied AI

   Future 3D motion prediction boosts robot learning with fewer demonstrations

   Trace-WAM: Learning to Act via 3D Motion Prediction for World Action Models

   The method, Trace-WAM, jointly predicts future video, 3D motion, and actions, improving performance on several benchmarks and real-world tasks, especially when data is limited.

   LIBERO: 98.7% success rate (as reported)

   30 Oct 2026The Hong Kong Polytechnic University, Alibaba Group, Tsinghua University

2. Research · Robotics & embodied AI

   Robots can act at 50 Hz while updating visual understanding once a second

   Leap-VLA: High-Rate Robot Control from a Low-Rate VLM Backbone

   Cached semantic context plus a fast visual stream allows robot control at 20-50 Hz with 1-second VLM updates, recovering over 94% success rate.

   LIBERO Goal: 97.2% success rate (as reported)

   3 Nov 2026Leapmotor

3. Research · Robotics & embodied AI

   Robots can use human videos before learning their own controls

   RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions

   Zhao and colleagues pretrained a robot policy on motion representations extracted from 30,100 hours of video, then adapted it to specific robots and evaluated manipulation performance.

   LIBERO: 98.8% success (as reported)

   30 Oct 2026Hong Kong Embodied AI Lab, CUHK, PUMC

4. Research · Robotics & embodied AI

   Robots learn tasks better with demonstrations generated by a video model

   RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions

   Zhao and colleagues report that a model trained across human, robot and simulation videos generates additional demonstrations that improve robot policy success in the evaluated settings.

   LIBERO: 97.8% success rate (as reported)

   30 Oct 2026Hong Kong Embodied AI Lab, CUHK, DAMO Academy, Alibaba Group

5. Research · Efficiency & systems

   Robot fleets can finish more work with fewer active robots

   Serving Agentic Robot Fleets: Workload Characterization, KV-Cache Thrashing, and Admission Control

   In sustained replay of robot workloads, limiting active episodes restored shared computing throughput and roughly quadrupled completed programs.

   LIBERO-PRO: 0.81 median turn rate per second of environment time (as reported)

   3 Nov 2026Huawei Inc.

6. Research · Robotics & embodied AI

   Scoring imagined futures and actions before execution triples robot success rates

   Seeing Through the Illusion: Test-Time Scaling for World Action Models

   A frozen world model that generates both actions and predictions can be made four times more reliable by evaluating candidates on action validity, inverse-dynamics consistency, and task progress before acting.

   LIBERO: 3.5 x relative episode runtime (as reported)

   3 Nov 2026Huawei Technologies Canada, University of British Columbia

7. Research · Robotics & embodied AI

   Robots can borrow a video model's foresight and act 21 times faster

   W2A: Distilling World Priors into Action Models for Real-Time Robotic Control

   A two-stage training method transfers what a video prediction model has learned about how scenes unfold into a robot control model, then throws the video model away before deployment.

   LIBERO: 95.9% success rate (as reported)

   3 Nov 2026Harbin Institute of Technology, Shenzhen