These findings motivate Action-Relevant Predictive States (ARPS), a compact predictive interface between the video and action experts that achieves 99.2% success on LIBERO and transfers to LIBERO-Plus without adaptation, reaching 87.3% and exceeding Fast-WAM by 39.2 percentage points.
Qiwen Gu, Ji-Fan Li, Bing-Jie Gao et al.· 0 citations
The results of R2M-Bench support same-rollout relative calibration as a practical way to distinguish revisit-specific consistency from generic temporal stability.
Inspired by render-based compression, this work renders textual chains of thought into images, extract visual features, and construct a discrete latent vocabulary via clustering-based fine-tuning, and concludes that discrete latent tokens provide a controllable and interpretable basis for efficient latent reasoning.
Shuochen Chang, Qingyang Liu, Shaobo Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.