activity
20242026
collaborators

13 papers

cs.LG2026

CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA

Gengyu Zhang, Haiyin Ran, Zhengbao He +4

As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently…

cs.LG2026

SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector

Jingyuan Zhang, Yucheng Bai, Peixi Wen +6

Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off b…

cs.LG2026

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter

Zhengbao He, Ruiqi Ding, Zhehao Huang +3

Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapt…

cs.LG2026

Remaining-data-free Machine Unlearning by Suppressing Sample Contribution

Xinwen Cheng, Zhehao Huang, Wenxin Zhou +4

Machine unlearning (MU) aims to remove the influence of specific training samples from a well-trained model, a task of growing importance due to the ``right to be forgotten.'' The…

cs.LG2026

RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format

Zhehao Huang, Yuhang Liu, Baijiong Lin +5

Large reasoning models (LRMs) excel at a long chain of reasoning but often fail to faithfully follow instructions regarding output format, constraints, or specific requirements. We…

cs.LG2025

Towards Natural Machine Unlearning

Zhengbao He, Tao Li, Xinwen Cheng +2

Machine unlearning (MU) aims to eliminate information that has been learned from specific training data, namely forgetting data, from a pre-trained model. Currently, the mainstream…