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

199 results on this page · clear filters

machine learning Oct 02 From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation by Siqi Zhu, Suozhi Huang, Kaixuan Zhang, Yuheng Yang, Zhanyang Jin, Yihang Sun, Jiaxuan You machine learning Oct 02 Effective Resistance and Graph Neural Network Reliability in Tissue-Specific Interactomes by Jianru Shen machine learning Oct 02 Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair by Areeb Ahmad, Pratinav Seth, Vinay Kumar Sankarapu machine learning Oct 02 When Do Intrinsic Rewards Lead to Exploration? by Scott W. Viteri (Stanford University), Laura Gomezjurado Gonzalez (Stanford University), Clark Barrett (Stanford University) machine learning Oct 02 Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials by Nikolaos Makras, Sotirios Sabanis machine learning Oct 02 Faynt: Scaling and Optimizing Policies for Competitive Melee by Ali Janati, Nikita Kuzmin, Rohit Swamy, Charles Niu machine learning Oct 02 Finetuning with Sampling: SFT Learns Better Than You Think by Aayush Karan, Sitan Chen, Yilun Du machine learning Oct 02 Linear Programming Representations and Strongly Polynomial Algorithms for Robust Markov Decision Processes by Han Zhong, Yinyu Ye machine learning Oct 02 Local Support Learning by Assaf Ben-Kish, Akarsh Kumar, James Glass, Raja Giryes machine learning Oct 02 Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability by Chuqin Geng, Li Zhang, Haolin Ye, Mark Zhang, Luke Zhang, Xujie Si