WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published 12 days ago • 142
a3ilab-llm-uncertainty/gptoss_20b_all_zhtw_lr5e-7_ep5_64_128_256_2_1_2_llamafactory_oringal_train Text Generation • Updated Jul 26 • 1
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published Jun 11 • 114