WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published 3 days ago • 134
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill Paper • 2608.11924 • Published 16 days ago • 289
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization Paper • 2607.25659 • Published Jul 28 • 84
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes Paper • 2607.13188 • Published Jul 14 • 34
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction Paper • 2607.01764 • Published Jul 2 • 8
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence Paper • 2605.30093 • Published May 28 • 15