Papers

Deep, long-form breakdowns of recent research in AI, machine learning, security & programming languages.

All ai machine learning cybersecurity scraping programming languages technology Important

198 results on this page · clear filters

machine learning Oct 23 SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing by Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe, Huy Nghiem, Yongkyun Lee, Andrew Adams Schoen, Furong Huang machine learning Oct 23 METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning by Ali Najar, Hosein Hasani, Amir Kooshan Fattah, Yasamin Rajabi, Mahdieh Soleymani Baghshah machine learning Oct 23 Low-Bit N-Gram Embeddings for Language Models by Stephen Chung, Wenyu Du machine learning Oct 23 A Fix for Softmax and Cross-Entropy by Jonathan T. Barron, Dan Gnanapragasam, Michael Tschannen machine learning Oct 23 WorldForge V2: Eliciting Camera-Trajectory Alignment in Video Diffusion Models by Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Joey Tianyi Zhou, Chi Zhang machine learning Oct 23 Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation by Gabriele Dominici, Teague McMillan, Fazl Barez, Marc Langheinrich, Martin Gjoreski machine learning Oct 23 BeNice! Closing Looping's Inference-Memory Gap via KV-Sharing by Hayden Prairie, Jacob M. Ryan, Taylor Berg-Kirkpatrick, Daniel Y. Fu machine learning Oct 23 Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3 by Barış Alparslan, Sandy Tanwisuth, Caleb Petterson machine learning Oct 23 OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation by Qi Li, Xinchao Wang machine learning Oct 23 Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy by Gautam Kamath, Mahbod Majid, Ankur Moitra, Argyris Mouzakis, Jonathan Ullman