📄 Paper Explainer

All Explained Papers · cs.LG

1727 papers in cs.LG. Page 7 of 87. ← Back to home

• arXiv:2608.19073 · cs.AI+2 · submitted 2026-08-19 · explained 2026-08-20
  Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
  Deep Kumar Ganguly, Jan Křetínský
• arXiv:2608.19140 · cs.AI+3 · submitted 2026-08-19 · explained 2026-08-20
  6mm Grouping the Stochastic Machine[1.5mm] Precision, Not Capability, as the Frontier Metric for AI Systems-2mm
  George Andrikopoulos
• arXiv:2607.14169 · cs.AI+1 · submitted 2026-07-15 · explained 2026-08-19
  When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models
  Javier Aguilar Martín
• arXiv:2607.08789 · cs.LG+3 · submitted 2026-06-26 · explained 2026-08-19
  Adaptive Bayes exactly tracks information over intrinsic time
  Akshay Balsubramani
• arXiv:2607.06382 · stat.ML+1 · submitted 2026-07-07 · explained 2026-08-19
  A Function-Space Dichotomy for Compositional Learning: Exponential Sub-Optimality of the Neural Tangent Kernel
  Arkaprabha Ganguli, Emil Constantinescu
• arXiv:2605.27483 · cs.CL+2 · submitted 2026-05-26 · explained 2026-08-19
  Debate Helps Weak Judges Reward Stronger Models
  Ethan Elasky, Frank Nakasako, Naman Goyal
• arXiv:2605.22496 · cs.LG · submitted 2026-05-21 · explained 2026-08-19
  The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
  Philipp Bomatter, Jack Geary, Henry Gouk
• arXiv:2604.17121 · cs.LG+1 · submitted 2026-04-18 · explained 2026-08-19
  The Topological Trouble With Transformers
  Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne Liu
• arXiv:2604.15945 · cs.CL+1 · submitted 2026-04-17 · explained 2026-08-19
  RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration
  Fabian Ridder, Laurin Lessel, Malte Schilling
• arXiv:2604.15149 · cs.LG+1 · submitted 2026-04-16 · explained 2026-08-19
  LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
  Lukas Helff, Quentin Delfosse, David Steinmann, et al.
• arXiv:2604.00842 · cs.AI+2 · submitted 2026-04-01 · explained 2026-08-19
  0.5~ Active Users to Evaluate Proactive Assistants
  Deepak Nathani, Cheng Zhang, Chang Huan, et al.
• arXiv:2603.22293 · cs.CL+2 · submitted 2026-03-11 · explained 2026-08-19
  TIPS: Turn-level Information-Potential Reward Shaping for Search-Augmented LLMs
  Yutao Xie, Nathaniel Thomas, Nicklas Hansen, et al.
• arXiv:2601.07320 · cs.LG+1 · submitted 2026-01-12 · explained 2026-08-19
  Segmental Advantage Estimation: Enhancing PPO for Long-Context LLM Training
  Xue Gong, Qi Yi, Ziyuan Nan, et al.
• arXiv:2510.17671 · cs.LG+2 · submitted 2025-10-20 · explained 2026-08-19
  Bayesian Optimization with Natural Language Feedback
  Katarzyna Kobalczyk, Zhiyuan Jerry Lin, Benjamin Letham, et al.
• arXiv:2510.14967 · cs.CL+2 · submitted 2025-10-16 · explained 2026-08-19
  Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
  Guoqing Wang, Sunhao Dai, Guangze Ye, et al.
• arXiv:2509.24527 · cs.AI+3 · submitted 2025-09-29 · explained 2026-08-19
  Training Agents Inside of Scalable World Models
  Danijar Hafner, Wilson Yan, Timothy Lillicrap
• arXiv:2509.18611 · cs.LG+1 · submitted 2025-09-23 · explained 2026-08-19
  Flow Marching for a Generative PDE Foundation Model
  Zituo Chen, Sili Deng
• arXiv:2508.03680 · cs.AI+1 · submitted 2025-08-05 · explained 2026-08-19
  Agent Lightning: Train ANY AI Agents with Reinforcement Learning
  Xufang Luo, Yuge Zhang, Zhiyuan He, et al.
• arXiv:2507.17746 · cs.LG+2 · submitted 2025-07-23 · explained 2026-08-19
  Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
  Anisha Gunjal, Anthony Wang, Elaine Lau, et al.
• arXiv:2507.01831 · cs.LG+1 · submitted 2025-07-02 · explained 2026-08-19
  Out-of-Distribution Detection Methods Answer the Wrong Questions
  Yucen Lily Li, Daohan Lu, Polina Kirichenko, et al.