2026 顶会论文
8作者位次 #4/5ICML 2026Oral· General Machine Learning / Data
Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders
Zhongzhi Li · Xuansheng Wu · Yijiang Li · Lijie Hu · Ninghao Liu
作者位次 #4/4ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
Xinyan Jiang · Ninghao Liu · Di Wang · Lijie Hu
作者位次 #6/6ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Algorithmic Recourse of In-Context Learning for Tabular Data
Wenshuo Dong · Jiaming Zhang · Shaopeng Fu · Hongbin Lin · Di Wang · Lijie Hu
作者位次 #3/3ICML 2026Poster· Theory / Learning Theory
Understanding Generalization and Forgetting in In-Context Continual Learning
Guangyu Li · Meng Ding · Lijie Hu
作者位次 #3/3ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Bayesian Gated Non-Negative Contrastive Learning
Peng Cui · Jiahao Zhang · Lijie Hu
作者位次 #7/7ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Multi-Adapter Representation Interventions via Energy Calibration
Manjiang Yu · Hongji Li · Junwei Chen · Xue Li · Priyanka Singh · YANG CAO · Lijie Hu
作者位次 #7/7ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Beyond Fixed Biases: Decoding the Role of Reasoning Uncertainty in MLLM Modality Conflicts
Zhuoran Zhang · Tengyue Wang · Xilin Gong · Yang Shi · Haotian Wang · Di Wang · Lijie Hu
作者位次 #4/6ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring
Guanxu Chen · Jing Shao · Tao Luo · Lijie Hu · Qihao Lin · Dongrui Liu