Search

Reinforcement Learning via Self-Distillation (SDPO)

A user-friendly & efficient knowledge distillation framework for LLMs, supporting off-policy, on-policy (OPD), cross-tokenizer, multimodal, and on-policy self-distillation.

Official Repo of "D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models"

Official implementation for "Towards a Unified Self-Distillation Framework for Large Language Models" (https://arxiv.org/abs/2605.06597).

On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

🔥 On-Policy Self-Distillation in Diffusion Models