Hugging Face daily papers·2d agoUniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement#unievo-vl#self-distillation#multimodal
Hugging Face daily papers·7d agoAligning One-Step Generative Models with Reward-Weighted Transport Distillation#generative-models#distillation#reward-model