2026 顶会论文
7作者位次 #4/6ICML 2026Poster· Deep Learning / Large Language Models
Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
Qinghe Ma · Zhen Zhao · Yiming Wu · Jian Zhang · LEI BAI · Yinghuan Shi
作者位次 #2/3ICML 2026Poster· Social Aspects / Safety
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
Tongxi Wu · Jian Zhang · Yang Gao
作者位次 #3/6ICML 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning
When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
Yayuan Li · Ze Peng · Jian Zhang · Jintao Guo · Yue Duan · Yinghuan Shi
作者位次 #3/6CVPR 2026Poster· Computer Vision & Pattern Recognition
Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decoding
Shumeng Li · Jintao Guo · Jian Zhang · Yulin Zhou · Luyang Cao · Yinghuan Shi
作者位次 #3/5CVPR 2026Poster· Computer Vision & Pattern Recognition
One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
Zhan Fa · Yue Duan · Jian Zhang · Lei Qi · Yinghuan Shi
作者位次 #5/7KDD 2026Oral· Knowledge Discovery & Data Mining
SocraticChem: Physics-Grounded Socratic Inquiry for Safety-Critical Experimental Science
Jianhang Ye · Wanqi Yang · Bo Zhang · Zekun Li · Jian Zhang · Ming Yang · Yinghuan Shi
作者位次 #3/6AAAI 2026Poster· Artificial Intelligence
Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA
Zhan Fa · Yue Duan · Jian Zhang · Lei Qi · Wanqi Yang · Yinghuan Shi