Changsheng Wang
~Changsheng_Wang1
3
论文总数
3.0
年均投稿
平均评分
接收情况3/3
会议分布
ICML
1
NeurIPS
1
COLM
1
发表论文 (3 篇)
20253 篇
4
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
ICML 2025Poster
4
The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
NeurIPS 2025Spotlight
3
LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
COLM 2025Poster