Released GenLIP, a generative pretraining framework for Vision Transformers.

ByteDance introduced OmniShow, a unified multimodal framework for video generation.

Introduces Helios, a 14B parameter video generation model running at 19.5 FPS on a single H100 GPU.

Collaborated with Tsinghua University and Peking University to develop the HACPO research framework.

Introduced Mixture-of-Depths Attention (MoDA) for deep LLMs

Postponed global launch of Seedance 2.0 AI model due to copyright complaints