We have 6 of 9 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Diffusion language models (DLMs) offer a promising alternative to autoregressive (AR) language generation. Recent advances in continuous DLMs, which apply latent diffusion to continuous text embeddings, raise a practical question: which embedding makes the best latent space, i.e., the most diffusible? To answer this, w...
This work proposes Visual Contrastive Self-Distillation, namely VCSD, which converts image-content removal into an on-policy self-distillation signal, and consistently outperforms matched OPSD across Qwen3-VL and Qwen3.5 models.
Self-Supervised Visual On-Policy Distillation (S$^2$VOPD), a simple yet effective method that constructs on-policy learning signals from asymmetric augmented views, systematically explores a broad design space of visual augmentations and uncover that asymmetry matters.
Clue-OPSD, a clue-privileged on-policy self-distillation framework for long-video understanding that uses clue intervals as privileged supervision without relying on ground-truth answer labels, while requiring no clue annotations or additional modules at inference time is introduced.
U-OPSD first samples multiple rollouts and constructs a pseudo solution by majority vote under a self-consistency threshold, and conditions the model's distribution on the pseudo-solution and distills itself on the disagreeing completions, allowing the model to correct itself precisely where it is confidently wrong.
This work introduces Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers, and shows that unsupervised reasoning can emerge through cooperative multi-agent training.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
