文生视频大模型笔记
A three-part technical note on text-to-video large models, covering probabilistic generation, video diffusion Transformers, system engineering, evaluation, long-video generation, post-training, safety, and research directions.
Read more
A three-part technical note on text-to-video large models, covering probabilistic generation, video diffusion Transformers, system engineering, evaluation, long-video generation, post-training, safety, and research directions.
Read moreA note of gratitude to my advisors, dissertation committee, family, and friends, guided by a small personal credo: love, sincerity, and courage.
Read more