作者位次 #5/10ICLR 2026Poster· Social Aspects / Accountability, Transparency and Interpretability
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
Yuntai Bao · Xuhong Zhang · Jintao Chen · Ge Su · Yuxiang Cai · Hao Peng · SUN Bing · Haiqin Weng · Liu Yan · Jianwei Yin