Skip to content

Author

Kang-Hui Tian

We have 5 of 12 papers

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.

Sep 2026

Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation

On-policy distillation (OPD) improves reasoning by providing token-level supervision from a teacher on a student's own trajectories. Existing methods primarily focus on enhancing this teacher-side guidance (e.g., by enriching teacher inputs and refining teacher feedback), yet we find that limited student perception is...

Si-Yuan Liu, Kang-Hui Tian, Yue Duan et al. · 0 citations
#machine learning Preprint Nov 2026

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

TurnWise is proposed, a turn-level GRPO framework that aligns learning with individual streaming decisions and addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy in streaming video understanding.

Shuai Dong, Kang-Hui Tian, Ling-Han Chen et al. · 0 citations
#machine learning Preprint Sep 2026

RL Starts before RL: On Policy Distillation for Better Reinforcement Learning

The results support OPD as preparation for RL and favor forward KL when OPD is followed by RL in the authors' comparison, which highlights the importance of both objective choice and the states receiving supervision for subsequent RL.

Shuai Dong, Yong-Fu Zhu, Yu-Qi Xu et al. · 3 citations · ⚡1
#artificial intelligence Preprint Sep 2026

What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation

This work compares the student view and training fixed within each scale against three abstractions compiled offline, a named strategy, a method-independent framing, and a problem category, and against an answer-only control that keeps the destination but removes the path.

Kang-Hui Tian, Si-Yuan Liu, Tianxiang Jiang et al. · 2 citations
#artificial intelligence Preprint Sep 2026

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Value Flattening is identified as an important yet overlooked failure mode of critic learning in standard PPO and a simple sparse supervision strategy can mitigate it; SParse Proximal Policy Optimization is introduced, which applies the value loss to only a few well-separated states in each response to mitigate both ef...

Yi-Zhuo Li, Jian-Hao Yan, Yun Luo et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.