Sudoku

Researchers introduced Latent Recurrent Thoughts (LRT), a method that enables frozen large language models to reason in continuous representation space using a small recurrent reasoner, outperforming …

Researchers introduced Reflective Masking (RM), a post-training method that enables Mask Diffusion Models to iteratively revise their own outputs by re-masking uncertain tokens and remembering previou…

Researchers have developed Discrete Tilt Matching (DTM), a likelihood-free method for fine-tuning masked diffusion large language models using reinforcement learning. The approach recasts fine-tuning …