Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning
by Ismail Labiad, Matthieu Kowalski, Marc Schoenauer, Rémi Munos, Julia Kempe
Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation
by Lijuan Tang, Yuemeng Zheng
Detecting GPT-Assisted Writing Using Interpretable Stylometric Features
by Rajesh Kumar, Nabeel Siddiqui, Alexander Fuchsberger
From Alignment to Access Control: A Framework for GenAI Policy Enforcement
by Nathalie Baracaldo
Decoding the Legalese: A Scalable and Quantitative Framework for Analyzing Corporate Privacy Policies
by Jiaming Tang, Chenlan Wang, Mingyan Liu, Armin Sarabi
A Spectral Theory of Grokking: Weight Decay induces Feature Learning
by Lenz Pracher, Pascal de Jong, Oskar Lieshaus, Alan Jeffares, Steffen Rulands
MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning
by Kairui Yang, Ziheng Yi, Xunkai Li, Minghao An, Zhanke Liu, Zekai Chen, Rong-Hua Li
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
by Yiran Wang, Xingyilang Yin, Junfu Pu, Guangzhi Wang, Kaifeng Li, Mingyu Ouyang, Huiqiang Sun, Lingen Li, Cheng Cheng, Wangbo Yu, Honghao Chen, Xiaodong Cun, Chi-Man Pun, Zhiguo Cao, Ying Shan
MIGU: Multimodal Instruction Grounding under Uncertainty for Manipulation Planning
by Mingke Lu, Anxing Xiao, David Hsu
Feedback Coding Enables Inference-Time Covert Agentic Communication
by Sidong Guo, Sajani Vithana, Atefeh Gilani, Lalitha Sankar, Oliver Kosut, Flavio P. Calmon