{"total":15,"rows":[{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2509.26313","title":"One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2507.00721","title":"UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2606.03070","title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2605.08887","title":"Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2607.00164","title":"Verifiable Rewards for Calibrated Probabilistic Forecasting","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2601.22920","title":"Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.02178","title":"AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.08905","title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.10445","title":"Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.06671","title":"Tracking the Moving Frontier: Long-Short Term Advantage Estimator","created":"2026-09-06","cited_by_count":0,"area":null}],"next_cursor":null}