A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
ProcessThinker enhances multi-modal large language models' reasoning via rollout-based process reward, improving step-level feedback for test-time scaling.
Ruoyu Qin, Weiran He, Weixiao Huang, et al.
Seer is a context-learning RL system that reduces long-tail latency by 72-94% and improves rollout throughput by 2.04x through divided rollout, context-aware scheduling, and adaptive grouped speculative decoding.
Peiyi Wang, Lei Li, Zhihong Shao, et al.
Math Shepherd automatically scores each reasoning step in math solutions using MCTS-inspired rollouts, enabling step-by-step PPO without human annotations.