Search

3 results for “LIBERO-Plus”

1. 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

2. 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

3. Research · Robotics & embodied AI

   Observation-only videos can directly pretrain robot action policies

   Native Action-Prior Learning from Videos for World Action Models

   NAVA-WAM uses visual-transition prediction to train an action model before adapting it with action-labeled robot demonstrations.

   LIBERO-Plus: 83.5% success rate (as reported)

   5 Oct 2026Meta AI, University of Copenhagen, Physical Intelligence