Publication Self-distilled Attention Gating for Efficient Long-context Prefilling Yizhao Gao, Zhichen Zeng, DaYou Du, Shijie Cao, Peiyuan Zhou, Jiaxing Qi, Junjie Lai, Hayden Kwok-Hay So, Ting Cao, Fan Yang, Mao Yang NeurIPS 2025 | October 2025
Publication Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming Alex Chouldechova, A. Feder Cooper, Solon Barocas, Abhinav Palia, Dan Vann, Hanna Wallach NeurIPS 2025 | October 2025
Publication IndiMathBench: Autoformalization Mathematical Reasoning Problems with a Human Touch Param Biyani, Shashank Kirtania, Yasharth Bajpai, Ashish Tiwari, Sumit Gulwani ArXiv | October 2025
Publication Leveraging Large Language Models to Generate Multiple-Choice Questions for Ophthalmology Education Shahrzad Gholami, Daniel B. Mummert, Beth Wilson, Sarah Page, Rahul Dodhia, Juan M. Lavista Ferres, Bill Weeks, Dale E. Fajardo, Karine D. Bojikian JAMA Ophthalmology | October 2025 Project
Publication Corporate Biodiversity Reporting Can Be Scaled with AI and Earth Observation—But Will Miss the Point Without Guidance from Conservation Scientists Benjamin L. Miller, Seamus Lombardo, Amy Rosenthal, Tara O'Shea,, Amy Luers, Juan M. Lavista Ferres, Lisa Mandle, Taylor H. Ricketts, Stephen Polasky, Daniel G. Brown Society for Conservation Biology – Conservation Letters | October 2025
Publication Table-based language models for ophthalmology assessment in the emergency department Juan M. Lavista Ferres, Shu Feng, Mary Kim, Nadia Popovici, Lauren Lee, Kaden Moore, Karine D. Bojikian Graefes Arch Clin Exp Ophthalmology | October 2025
Publication Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness Erfan Shayegani, Keegan Hines, Yue Dong, Nael B. Abu-Ghazaleh, Roman Lutz, Spencer Whitehead, Vidhisha Balachandran, Besmira Nushi, Vibhav Vineet ICLR 2026 | October 2025
Publication Safe, Efficient, and Robust Reinforcement Learning for Ranking and Diffusion Models Shashank Gupta October 2025 PhD Thesis: University of Amsterdam | October 2025
Publication Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models Sofiane Ennadir, Levente Z'olyomi, Oleg Smirnov, Tianze Wang, John Pertoft, Filip Cornell, Lele Cao NeurIPS 2025 | October 2025
Publication PZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks Pengyun Yue, Xuanlin Yang, Mingqing Xiao, Zhouchen Lin NeurIPS 2025 | October 2025