On-policy distillation (OPD) is increasingly applied to frontier foundation model post-training. Prior work in this area has largely focused on algorithmic advances, yet it remains unclear how much OPD depends on its training questions and, in particular, how far this dependence can be reduced. Across two representativ...
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· 0 citations
Long-form video understanding remains challenging for video agents due to the mismatch between query demands and evidence acquisition strategies. Although recent planning-before-perception methods outperform query-agnostic pipelines, they often rely on a single dominant strategy, either generation-based strategy or ret...
Tianyu Wang, Xu-Ying Wu, Yuxiang Ma et al.· 2 citations
Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero is proposed.
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.· arXiv.org· 24 citations· ⚡3
PixVL is a self-supervised post-training framework that introduces a unified Mask--Text Consistency Cycle, enabling pixel-level MLLMs to generate and self-verify regional descriptions and learn from unlabeled data.
Yi-Cheng Xiao, Hao-Xuan Ma, Caorui Li et al.· 0 citations
This work proposes PRISM, a new multi-reward RL framework built upon the idea of policy-space decomposition and composition, which alleviates the potential conflict during multi-reward policy optimization, while enabling controllability during inference by flexible policy composition.
DASH maps the gap between each local distillation signal and the sequence-level mean to an adaptive propagation gate and then uses these gates to control backward multi-step aggregation and improves over matched vanilla OPSD reruns on every benchmark at all three model scales.
Zhi-Yan Hou, Xinyu Tang, Hongyan An et al.· 3 citations
Anchored by this tri-axial framework, representative methods are systematically surveyed, the ongoing transition of continual learning is traced, and the key challenges, broader implications, and future directions arising from this paradigm shift are discussed.
Zhi-Yan Hou, Dan Zhang, Tao Feng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
