LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
Overview
This research presents LaST0.5, a novel World Action Model (WAM) designed to bridge the gap between global world modeling and precise robotic manipulation. The model introduces an interaction-centric latent space supervised by visual cues of robot-environment interactions, instantiated as a latent expert within a Mixture-of-Transformers architecture. By jointly predicting future representations and progress values, LaST0.5 adapts its world-to-action transfer using progress consistency to adjust action execution. Pretrained on over 14k hours of robotic data, the model achieves 99.5% success on the LIBERO benchmark and outperforms previous state-of-the-art methods on ten RLBench tasks, demonstrating robust long-horizon execution and dexterous manipulation in real-world experiments.
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · training_hours: 14000 hours · Basis not reported
“just action execution and trigger future resampling. Finally, we pretrain LaST0.5 on a large-scale robotic data corpus comprising over 14k hours of data, establishing interaction-centric physical reasoning as a scalable and effective paradigm. LaST0.5 achieves 99.5% on LIBERO, surpasses the previous state of the art on ten evaluated RLBench tasks, and demonstrates robust long-horizon execution and precise dexterous m”
Exact source · revision 1Source owner not reported
Reported quantity · tasks_evaluated: 10 other · reported trials
“just action execution and trigger future resampling. Finally, we pretrain LaST0.5 on a large-scale robotic data corpus comprising over 14k hours of data, establishing interaction-centric physical reasoning as a scalable and effective paradigm. LaST0.5 achieves 99.5% on LIBERO, surpasses the previous state of the art on ten evaluated RLBench tasks, and demonstrates robust long-horizon execution and precise dexterous m”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalLaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
This research presents LaST0.5, a novel World Action Model (WAM) designed to bridge the gap between global world modeling and precise robotic manipulation. The model introduces an interaction-centric latent space supervised by visual cues of robot-environment interactions, instantiated as a latent expert within a Mixture-of-Transformers architecture. By jointly predicting future representations and progress values, LaST0.5 adapts its world-to-action transfer using progress consistency to adjust action execution. Pretrained on over 14k hours of robotic data, the model achieves 99.5% success on the LIBERO benchmark and outperforms previous state-of-the-art methods on ten RLBench tasks, demonstrating robust long-horizon execution and dexterous manipulation in real-world experiments.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).