Haiguang Liu — accepted AI-conference papers

2026

FlexProtein: Joint Sequence and Structure Pretraining for Protein Modeling

Jianwei Zhu, Yu Shi, Ran Bi, Peiran Jin, Chang Liu, Zhe Zhang +17

ICLR 2026poster

Protein foundation models have advanced rapidly, with most approaches falling into two dominant paradigms. Sequence-only language models (e.g., ESM-2) capture sequence semantics at scale but lack structural grounding. MSA-based predictors (e.g., AlphaFold 2/3) achieve accurate folding by exploiting…

Cited by 0 Source ↗Scholar ↗

2026

Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization

Haodong Zhu, Ren Yangyang, Yanjing Li, Mingbao Lin, Linlin Yang, Xuhui Liu +3

ICML 2026poster

Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this overhead, they could induce estimation bias by altering the u…

Cited by 0 Source ↗Scholar ↗