Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models.
-
Diffusion Language Models Know the Answer Before Decoding
Paper ā¢ 2508.19982 ā¢ Published ā¢ 27 -
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Paper ā¢ 2512.13586 ā¢ Published ā¢ 93 -
LSRIF: Logic-Structured Reinforcement Learning for Instruction Following
Paper ā¢ 2601.06431 ā¢ Published ā¢ 12 -
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
Paper ā¢ 2601.09088 ā¢ Published ā¢ 62
