…Rethinking Optimization Granularity in On-Policy Distillation Published on Jun 1 Submitted by Hangjie Yuan on Jun 4 Tsinghua University Authors: , , , , , , , , Abstract FiRe-OPD improves on-policy distillation in large language models…
…Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation Published on May 27 Submitted by Tiehua Mei on May 28 #3 Paper of the day Fudan University Authors: Hongru Hou…
…Leveraging Multimodal Priors for Denoising in Representation Space Published on Jun 12 Submitted by Xichen Pan on Jun 15 AI at Meta Authors: Xichen Pan , , , , Shlok Kumar Mishra , Abstract RepFusion leverages multimodal…
Papers arxiv:2605.01640 Prescriptive Scaling Laws for Data Constrained Training Published on May 2 Submitted by Justin Lovelace on May 8 Authors: , , , , Abstract A modified scaling law accounts for data repetition…
…Transferring Knowledge from Noise Domain Published on May 30 Submitted by Yuan Yao on Jun 4 Authors: , , , , , Abstract A novel semi-supervised learning approach uses synthetic noise domains as source domains to…
Papers arxiv:2606.08132 Phase Marginalization for Patch-Grid Instability in Vision Transformers Published on Jun 6 Submitted by Oğuzhan Ercan on Jun 9 BILGEM AI Authors: Oğuzhan Ercan Abstract Phase Marginalization…
…Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning Published on Jun 2 Submitted by youyou on Jun 11 TongyiLab Authors: , Yingcheng Shi , , , , , , , Abstract EvoTrainer autonomously evolves both language…
…A Regime Map and Its Mechanism Published on May 29 Submitted by Haoxiang Zhang on Jun 2 McAuley-Lab Authors: Haoxiang Zhang , Qixin Xu , , Lei Zhang , , , Abstract Observation masking in long-horizon…
…Prompt Space Perturbation Broadens Reasoning Exploration Published on May 7 Submitted by Chengsong Huang on May 8 Authors: , Chengsong Huang , , , , Jiaxin Huang Abstract LoPE addresses the zero-advantage problem in reinforcement learning…
…Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams Published on Jun 1 Submitted by Zewen Liu on Jun 3 Authors: Zewen Liu , , , , , , , , , Abstract Adaptive Auto-Harness framework addresses…