activity
20242026
collaborators

6 papers

cs.AI2026

Probing RLVR training instability through the lens of objective-level hacking

Yiming Dong, Kun Fu, Haoyu Li +5

Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the trai…

cs.CL2026

GENERator: A Long-Context Generative Genomic Foundation Model

Wei Wu, Qiuyi Li, Yuanyuan Zhang +15

The rapid advancement of DNA sequencing has produced vast genomic datasets, yet interpreting and engineering genomic function remain fundamental challenges. Recent large language m…

cs.CL2025

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection

Wei Wu, Zhuoshi Pan, Chao Wang +6

Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challeng…

cs.CL2025

Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs

Wei Wu, Chao Wang, Liyi Chen +6

Proteins, as essential biomolecules, play a central role in biological processes, including metabolic reactions and DNA replication. Accurate prediction of their properties and fun…

cs.LG2025

A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery

Yiheng Zhu, Mingyang Li, Junlong Liu +7

Structure-based drug discovery (SBDD) is a systematic scientific process that develops new drugs by leveraging the detailed physical structure of the target protein. Recent advance…

cs.LG2024

ProtCLIP: Function-Informed Protein Multi-Modal Learning

Hanjing Zhou, Mingze Yin, Wei Wu +5

Multi-modality pre-training paradigm that aligns protein sequences and biological descriptions has learned general protein representations and achieved promising performance in var…