Preprint [arXiv]
Tian Du, Tiantong Wu, Yafei Wang, Mengyu Liu, Xingyan Chen, Mu Wang
TL;DR: A new benchmark asking whether LLMs can look at two company profiles and reason about whether the firms have a plausible collaboration opportunity, rather than merely being similar businesses.
Xinyu Yan, Boyang Chen, Jiaming Zhang, Tiantong Wu, Hong Xi Tae, Yichen He, Tiantong Wang, Yachun Mi, Yurong Hao, Yilei Zhao, Lei Xiao, Longtao Huang, Pengjun Xie, Wei Liu, Wei Yang Bryan Lim
TL;DR: The first multimodal benchmark for detecting AI-generated fraudulent refund evidence.
ICML 2026 [GitHub arXiv Hugging Face]
Gong Zhiren, Tiantong Wu, Jiaming Zhang, Fuyao Zhang, CHE WANG, Yurong Hao, Yikun Hou, Foo Ping, Yilei Zhao, Fei Huang, Chau Yuen, Wei Yang Bryan Lim
TL;DR: We introduce XDomainBench, a benchmark for interactive interdisciplinary scientific reasoning, and show that LLMs exhibit systematic reasoning collapse as cross-domain composition becomes more complex.
TL;DR: A lightweight framework that integrates federated learning and targeted unlearning for LLMs, formulating them as a joint multi-objective optimization task to enable privacy-preserving training and compliance with GDPR's right to be forgotten.