7 papers
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…
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…
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…
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…
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…
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…