activity
20242026
collaborators

7 papers

cs.LG2026

Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery

Shiji Zhou, Tianbai Yu, Zhi Zhang +4

Machine unlearning (MU) aims to efficiently remove sensitive or harmful memory from a pre-trained model. The key challenge is to balance the potential tradeoff between unlearning e…

cs.LG2026

Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models

Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai +8

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SF…

cs.CV2025

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1

Zhaoyi Li, Xiaohan Zhao, Dong-Dong Wu +2

Despite promising performance on open-source large vision-language models (LVLMs), transfer-based targeted attacks often fail against closed-source commercial LVLMs. Analyzing fail…

cs.LG2025

Learning Robust Diffusion Models from Imprecise Supervision

Dong-Dong Wu, Jiacheng Cui, Wei Wang +2

Conditional diffusion models have achieved remarkable success in various generative tasks recently, but their training typically relies on large-scale datasets that inevitably cont…

cs.LG2025

LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models

Yupeng Su, Ziyi Guan, Xiaoqun Liu +6

Large language models (LLMs) have seen substantial growth, necessitating efficient model pruning techniques. Existing post-training pruning methods primarily measure weight importa…

cs.CL2025

Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations

Zican Dong, Han Peng, Peiyu Liu +4

Mixture-of-Experts (MoE) models achieve a favorable trade-off between performance and inference efficiency by activating only a subset of experts. However, the memory overhead of s…