activity
20242026
most citedLLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered

Sijia Liu, Yicheng Lang, Soumyadeep Pal +6

Zeroth-order (ZO) optimization, learning from finite differences of function evaluations without backpropagation, has recently regained attention in deep learning due to its memory…

cs.LG2026

Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization

Yancheng Huang, Changsheng Wang, Chongyu Fan +7

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, an…

cs.LG2026

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization

Yicheng Lang, Changsheng Wang, Yihua Zhang +4

Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has rece…

cs.LG2025

Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization

Changsheng Wang, Xin Chen, Sijia Liu +1

Adapting pretrained large language models (LLMs) to code domains via supervised fine-tuning (FT) has been commonly used for code generation. However, we identify a previously under…

cs.LG2025

LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data

Changsheng Wang, Yihua Zhang, Dennis Wei +3

Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data, reinforcing biases, and producing harm…

cs.LG2025

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics

Chongyu Fan, Changsheng Wang, Yancheng Huang +2

Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model…