Search

9 results for “LIBERO-Plus”

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-Plus: 83.4% success rate (as reported)

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

2. Research · Robotics & embodied AI

   Compact robot policy uses lightweight memory to stabilize action generation

   REKI: Registering Knowledge in VLAs

   REKI combines public-data pretraining with cached register tokens that preserve recent visual context at less than 1 percent inference overhead.

   LIBERO-Plus: 4.3 pts success rate improvement from pretraining (as reported)

   16 Oct 2026Kyutai, Inria, École nationale des ponts et chaussées

3. Research · Safety & security

   Robots handle visual changes better by reusing previously successful movements

   Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution

   R2A retrieves motion primitives from past demonstrations and fuses them with frozen policy actions, lifting success rates by up to 12 points in simulation and 40 points on a real robot.

   LIBERO-Plus: 98.6% success rate (as reported)

   28 Oct 2026VinUniversity, VinRobotics, Hanoi University of Science and Technology

4. Research · Robotics & embodied AI

   Robots can anticipate physical changes without generating videos of the future

   PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

   PDRVLA extracts compact physical tokens from VLM features via future prediction objectives, achieving high success rates on four simulation benchmarks without online video generation.

   LIBERO-Plus: 89.9% success rate (as reported)

   28 Oct 2026Peking University, JD.com

5. 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-Plus: 84.7% success (as reported)

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

6. 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-Plus: 84.8% success rate (as reported)

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

7. Research · Robotics & embodied AI

   Reasoning supervision lets action models skip decoding without losing performance

   TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

   TacitVLA matched explicit-reasoning policies across four robotics and driving benchmarks while reducing action latency by up to 3.4 times.

   LIBERO-Plus: 72.9% Success (as reported)

   14 Oct 2026NVIDIA, New York University, University of California, Berkeley

8. Research · Generative media

   One-step action generation and asynchronous pipeline achieve real-time world action models

   RealtimeWAM: One-Step Asynchronous World Action Models

   RealtimeWAM uses teacher-anchored consistency distillation and cross-expert pipelining to accelerate Mixture-of-Transformers based world action models by up to 25x on H100 GPUs with less than 1% accuracy loss

   LIBERO-Plus: 73% success rate (as reported)

   6 Oct 2026Nanyang Technological University, Beihang University, Sensetime

9. Research · Robotics & embodied AI

   One Model Predicts Robot Futures and Chooses Actions

   SUAVE: Unified Video-Action Models via Masked Diffusion

   SUAVE uses masked diffusion over shared discrete tokens to generate video, robot actions, or both with the same model weights.

   LIBERO-Plus: 86.1% success rate (as reported)

   6 Oct 2026Columbia University, Toyota Research Institute