Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
by Oskar J. Hollinsworth, Alex F. Spies, Tigist Diriba, Adam Gleave, Chris Cundy
Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization
by Hanyang Li, Shao Tang, Daniel Thomas Braithwaite, Gregory Dexter, Leonardo Neves, Aman Gupta, Hiroto Udagawa, Abhishek Shivanna, Daniel Silva, Rohan Ramanath
Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
by Erin Crawley, Hidenori Tanaka
A Unified Bellman Operator for Safety-Critical Reinforcement Learning
by Nishanth Arun Rao, Royina Karegoudra Jayanth, Benjamin Eysenbach, Jaime Fernández Fisac
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
by Hongyu Li, Manyuan Zhang, Kaituo Feng, Shu Chen, Dian Zheng, Hao Li, Hao Yu, Zhangquan Chen, Zoey Guo, Ray Zhang, Shaofei Huang, Tianrui Hui, Linjiang Huang, Si Liu
WOVEN: Weaving Visual World Modeling into Multimodal LLMs
by Zheyu Fan, Yue Zhang, Mingkai Deng, Kangrui Wang, Qineng Wang, Canyu Chen, Jie Hao, Xing Fan, Chenlei Guo, Eric P. Xing, Mohit Bansal, Manling Li
ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI
by Shihab Ahmed, Md Sajidul Islam Sajid, Teryl Taylor, Frederico Araujo, Tariqul Islam
Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
by Christopher M. Stewart, Preston Botter, Natalie Sarabosing, Muye Zhang, Rachel Phinnemore, Shalini Ghosh, Hong Shen, Hoda Heidari
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
by Hongxing Li, Jinyue Su, Dingming Li, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
Learning Kilometer-Scale Weather Prediction with Global-Regional Alignment
by Guowen Li, Yang Liu, Yujie Wang, Qiuyan Sun, Haoyuan Liang, Juepeng Zheng, Hong Cheng, Haohuan Fu