Papers
Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.
Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
by Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif, Samer Ellaham, Cedric Schmitz
Don't Trust the Super-App: A Case Study of Russia's Max
by Richa Priyanka, Aaron Ortwein, Joel Reardon, Michael Specter, Piyush Kumar Sharma, Roya Ensafi
Generative Late-Interaction Embeddings For Visual Document Retrieval
by Mohamed Eltahir, Talal Aloushan, Rose Khairoalsendi, Jana Shata, Mohammed Alhassan, Leen Alrehaili, Tanveer Hussain, Naeemullah Khan
Thinking with Looped Flows
by Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom, Nicholas M. Boffi, İsmail İlkan Ceylan, Jinwoo Kim
SpecGuard: Inference-Time Backdoor Detection For Free
by Rui Wen, Ahmed Salem, Andrew Paverd, Mark Russinovich, Zheng Li
RAGTIMER 1.0: Rapid Rare-Event Partial State Space Construction for Stochastic VAS (extended version)
by Landon Taylor, Joshua Jeppson, Bingqing Hu, Lukas Buecherl, Zhen Zhang
Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech
by Chibuzor Okocha, Christan Earl Grant
Predicting Privacy Leakage from Weight Spectral Density
by Richard J. Preen, Jim Smith
Towards Tackling Application Logic Flaws through Autonomous Formal-Logic Modeling and Automated Reasoning
by Yiwei Fang, Yichen Liu, Ze Jin, Haoqiang Wang, Qixu Liu, Luyi Xing
A positive resolution of the gap-entropy conjecture
by P. M. Aronow, Nathan Kallus, Patrick Lopatto