15 papers
FACT: Failure-Aware Causal Training for World-Action Models
Quanquan Peng, Yutong Liang, Rui Yan +2
Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on the future-prediction ability…
RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
Hanan Gani, Tejal Kulkarni, Madhoolika Chodavarapu +2
Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional.…
Hallucination in World Models is Predictable and Preventable
Nicklas Hansen, Xiaolong Wang
Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the g…
Generating Robot Hands from Human Demonstrations
Sha Yi, Nicklas Hansen, Xueqian Bai +3
Robot learning has advanced rapidly in learning control, but learning the physical body of a robot remains much more difficult because jointly searching over design and control cre…
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models
Darrien McKenzie, Nicklas Hansen, Xiaolong Wang
Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems…
Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
Minghao Fu, Fan Feng, Nicklas Hansen +1
World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are o…