← Search

Hongtao Tian

2 accepted papers

2026

Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization

ICLR 2026poster

Critic-free methods like GRPO reduce memory demands by estimating advantages from multiple rollouts but tend to converge slowly, as critical learning signals are diluted by an abundance of uninformative samples and tokens. To tackle this challenge, we propose the **Dynamic Dual-Level Down-Sampling (…

Cited by 0SourceScholar
2025

Discriminative Policy Optimization for Token-Level Reward Models

ICML 2025poster

Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs) for optimizing policy models, positioning them as a promising approach to enhancing the capabilities of LLMs in complex reasoning tasks. Recent efforts have advanced PRMs from step-level to token-l…