Search

26 results for “LIBERO” · page 2 of 2

1. Research · Robotics & embodied AI

   Robot AI speed depends more on action generation than model size

   VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware

   Benchmarking 18 models with a seven-stage inference breakdown reveals that kernel fusion and few-step generation are key to real-time robot control.

   LIBERO-10: 2.6 speed-up (as reported)

   27 Oct 2026National University of Singapore, 0G Labs

2. Research · Robotics & embodied AI

   Caching frozen model states makes forward-only robot adaptation much faster

   VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models

   VLA-ZO accelerates memory-efficient adaptation by updating only action components and reusing vision-language conditioning across parameter perturbations.

   LIBERO camera-viewpoint shifts: 25.59 x speedup (as reported)

   8 Oct 2026UNIST

3. Research · Robotics & embodied AI

   Sensorimotor alignment predicts robot task success offline

   Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

   A training-free metric measures how well sensory representations match motion trajectories, correlating with closed-loop performance across model families and settings.

   Meta-World, Robosuite, Franka-Kitchen: 0.77 Pearson r (as reported)

   23 Oct 2026Rice University, NVIDIA

4. Research digest

   AI systems need better checks, not just stronger models

   Across agents, training and evaluation, the strongest evidence separates improving a proxy from improving the system that practitioners actually deploy.

   22 Oct 2026

5. Research · Robotics & embodied AI

   Context scheduling improves long-horizon robot video prediction

   Remembering What Matters for Long-Horizon Robotic World Models

   ReCAP method preserves initial scene and recent frames while discarding stale history, boosting fidelity and efficiency without retraining.

   LIBERO-90: 12% LPIPS curve AUC reduction (as reported)

   15 Oct 2026The Hong Kong University of Science and Technology (Guangzhou), North China Electric Power University, LIGHTSPEED

6. Research · Robotics & embodied AI

   Action-aware embeddings retrieve better robot experiences for future actions

   Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution

   Robota-Embed matches a robot’s current task and execution stage to useful recorded continuations, improving retrieval and downstream policy performance.

   LIBERO difficult subset: 92.8% success (as reported)

   15 Oct 2026NVIDIA, MIT, UCB