Skip to content

Author

Han-Wen Zhang

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Aug 2026

Grounding-Aware Self-Distillation for Visual Reasoning

Self-distillation reinforcement learning usually selects teacher traces by answer correctness. In multimodal tasks, that criterion is incomplete: a model can answer correctly from language priors without using the image, and distilling such a trace reinforces ungrounded reasoning. We introduce visual counterfactual sen...

Han-Wen Zhang · 0 citations

CollabFlow: Recursive Self-Improvement of Agent Collaboration

This work proposes CollabFlow, an RSI system of Learned Agent Collaboration: a trainable Collab-Director constructs teams of complete Agents, a frozen executor runs them, and each round's outcomes retrain the director, and each round's outcomes retrain the director.

Xiao Huang, Ming-Da Zhang, Jun-Min Zhang 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.