← Search

Manjiang Yu

2 accepted papers

2026

Multi-Adapter Representation Interventions via Energy Calibration

ICML 2026poster

Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs. However, we find that the appropriate intervention direction…

Cited by 0SourceScholar
2026

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models

CVPR 2026

Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging: intermediate chain-of-thought steps can still leak sensitive information even when final answers are forgotten, and over

Cited by 0SourceScholar