출판 SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar, Amin Saied October 2025 arXiv | October 2025
출판 RAI Advocacy: Communicative Strategies for Advancing Responsible AI in Large Technology Companies Jordan Duran, Samir Passi, Mihaela Vorvoreanu AI, Ethics, and Society | October 2025
출판 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
출판 Rationalized All-Atom Protein Design with Unified Multi-modal Bayesian Flow Hanlin Wu, Yuxuan Song, Zhe Zhang, Zhilong Zhang, Hao Zhou, Wei-Ying Ma, Jingjing Liu NeurIPS 2025 | October 2025
출판 RoboSeer: Video Generators Can Be Generalizable Robot Manipulators Yichao Shen, Fangyun Wei, Zhiying Du, Yaobo Liang, Yan Lu, Jiaolong Yang, Nanning Zheng, Baining Guo NeurIPS 2025 | October 2025
출판 Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders Ali Rasekh, Erfan Soula, Omid Daliran, Simon Gottschalk, Mohsen Fayyaz NeurIPS 2025 | October 2025
출판 Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations Shixin Li, Xiaojing Ma, Zewei Li, Xiaofan Bai, Pingyi Hu, Dongmei Zhang, Bin Benjamin Zhu NeurIPS 2025 | October 2025
출판 CADMorph: Geometry‑Driven Parametric CAD Editing via a Plan–Generate–Verify Loop Weijian Ma, Shizhao Sun, Ruiyu Wang, Jiang Bian NeurIPS 2025 | October 2025
출판 Learning outcomes with GenAI in the classroom: A review of empirical evidence Kathy Walker, Mihaela Vorvoreanu MSR-TR-2025-42 | October 2025 글쓴이 Microsoft 프로젝트
출판 PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks Pengyun Yue, Xuanlin Yang, Mingqing Xiao, Zhouchen Lin NeurIPS 2025 | October 2025