Author

Ganqu Cui

h-index 34 View on Semantic Scholar

We have 3 of 85 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.

#natural language process... May 2026

Draft-OPD: On-Policy Distillation for Speculative Draft Models

Draft-OPD, which uses target-assisted rollout for stable continuations and replays drafting from the verification-exposed error positions, allowing the drafter to learn from target feedback on both accepted and rejected proposals, focusing on the draft-induced errors that limit speculative acceptance.

Hao Lei, Ya-Fu Li, Haoran Zhang et al. · arXiv.org · 10 citations · ⚡1

#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

Review Aug 2026

SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning

This work introduces a student reference KL loss and mask the advantages of special termination tokens to mitigate the problem of excessive generation length and frequent truncation, and improves on science benchmarks such as HLE and HiPhO, suggesting that OPD transfers reasoning capabilities that generalize beyond the...

Hao-Nan He, Hao Lei, Yun Luo et al. · 5 citations · ⚡1