2026 NeurIPS 2026 Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models Yik Siu Chan, Jing Huang, Yanai Elazar, and Atticus Geiger NeurIPS, ICML Mechanistic Interpretability Workshop, 2026 2025 NeurIPS FoRLM Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models Yik Siu Chan*, Zheng-Xin Yong*, and Stephen H. Bach NeurIPS Foundations of Reasoning in Language Models, 2025 arXiv Code ICML 2025 Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions Yik Siu Chan*, Narutatsu Ri*, Yuxin Xiao*, and Marzyeh Ghassemi The Forty-Second International Conference on Machine Learning, 2025 arXiv Code ICML 2025 MIB: A Mechanistic Interpretability Benchmark Aaron Mueller*, Atticus Geiger*, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fiotto-Kaufman, and 15 more authors The Forty-Second International Conference on Machine Learning, 2025 arXiv Website 2024 NeurIPS 2024 MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making Yubin Kim, Chanwoo Park, Hyewon Jeong, Yik Siu Chan, Xuhai Xu, Daniel McDuff, Hyeonhoon Lee, Marzyeh Ghassemi, and 2 more authors The Thirty-eighth Annual Conference on Neural Information Processing Systems (Oral), 2024 arXiv Website