3 accepted papers
We aim to improve the reasoning capabilities of language models via reinforcement learning with verifiable rewards (RLVR). Recent RLVR post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies suggest that using RLVR alone to…
We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT performs well for autoregressive models, its use in DLMs faces challenges. Our observation and analysis reveal that vanilla SFT does not consider learnability, i.e., what and when tokens are learned. Specific…
A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user preferences. However, user preferences vary significantly across…