BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM ...
Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, and Zhen Zhang.Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.URL h...