Reinforcement learning with verifiable rewards has substantially advanced multimodal reasoning, yet it remains fundamentally limited by ambiguous token-level credit assignment. While high-entropy token heuristics encourage possibility exploration, naively extending them to video reasoning tends to induce lengthy reason...
Yu-Dong Han, Yong Wang, Zai-Quan Yang et al.· 0 citations
Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and...
On-policy distillation (OPD) has emerged as an effective post-training paradigm for language models, with recent efforts extending it to block diffusion language models (BDLMs). However, existing studies focus almost exclusively on small block sizes, leaving distillation into student models with larger blocks underexpl...
Zai-Quan Yang, Fei Wei, Yong Wang et al.· 0 citations
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.
IntBMoE is a block-conditioned MoE that decouples all three by pairing dense expert composition with sparse block execution, and shows consistent gains over representative sparse and dense MoE baselines on image classification.
Ran Cheng, Long-Fei Xu, Zheng Liu et al.· 0 citations
SkillForge is proposed, a framework for continuous skill evolution that enables skills to be verified and refined through environment interaction and introduces evidence-based skill verification and multi-pathway skill induction, allowing the skill bank to continuously grow while maintaining its quality.
Shidong Yang, Zi-Yu Ma, Tongwen Huang et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
