Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
by Damiano Da Col, Maximilian Igl, Peter Karkus, Kashyap Chitta, Boris Ivanovic, Marco Pavone, Konrad Schindler, Christos Sakaridis
RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
by Mingxuan Zhang, Xiaowen Wang, Anupma Sharan, Zhengyi Chen, Chenyu Diana Zhang, Shanshan Yang, Chittibabu Pacharu
MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving
by Thomas Steinecker, Denis Trescher, Alexander Bienemann, Thorsten Luettel, Mirko Maehlisch
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
by Haocheng Xi, Yiming Xie, Hexu Zhao, Yiwen Zhang, Michael Liu, Thomas Creavin, Kurt Keutzer, Xiuyu Li, Zhaoyang Lv, Chenfeng Xu, Haiwen Feng
Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
by Zofia Smoleń
Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
by Frank E. Bobe III, Gregory D. Vetaw, Darshan W. Bryner, Matthew G. Cook, Jose L. Salas-Vernis
Large Language Models as Falsifiers for Cyber-Physical Systems
by Ali ArjomandBigdeli, Jiawei Zhou, Stanley Bak
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
by Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah
Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol
by Levent Bulut
Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation
by Lili Wang, Jing Li, Xiaowen Sun, Xiangyu Hu, Zhuangzhuang Gu, Jian Liu, Srihari Nelakuditi, Yan Tong