collaborators

5 papers

cs.LG2025

The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View

Xinhao Yao, Lu Yu, Xiaolin Hu +4

The ongoing debate on whether reinforcement learning with verifiable rewards (RLVR) expands or shrinks the reasoning capabilities of large language models (LLMs) remains unresolved…

cs.CL2025

Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained Knowledge

Pengwei Tang, Xiaolin Hu, Yong Liu +4

Low-Rank Adaptation (LoRA) is the leading parameter-efficient fine-tuning method for Large Language Models (LLMs), but it still suffers from catastrophic forgetting. Recent work ha…

cs.CL2025

Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization

Zixuan Gong, Xiaolin Hu, Huayi Tang +1

Large language models (LLMs) have demonstrated remarkable in-context learning (ICL) abilities. However, existing theoretical analysis of ICL primarily exhibits two limitations: (a)…

cs.LG2025

Chemical knowledge-informed framework for privacy-aware retrosynthesis learning

Guikun Chen, Xu Zhang, Xiaolin Hu +3

Chemical reaction data is a pivotal asset, driving advances in competitive fields such as pharmaceuticals, materials science, and industrial chemistry. Its proprietary nature rende…

cs.CL2025

ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Pengwei Tang, Xiaolin Hu, Yong Liu

Prompt Tuning (PT) enables the adaptation of Pre-trained Large Language Models (PLMs) to downstream tasks by optimizing a small amount of soft virtual tokens, which are prepended t…