Researchers from UCLA and Meta AI have introduced d1, a novel framework using reinforcement learning (RL) to significantly enhance the reasoning capabilities of diffusion-based la ...

My low-quality and poor-performance codes submitted to several online judges, such as ZeroJudge, GreenJudge, UVa, TIOJ, AtCoder, CSES problem set, LeetCode, Codeforces & Google Kick Start.