ByteDance's Next-Gen Video Model with Native Audio-Video Joint Generation
Added Feb 12, 2026
Seedance 2
Why: Seedance 2.0 represents the new frontier of multimodal generation, being one of the first models to generate high-fidelity audio and video simultaneously with extreme temporal consistency and physics-based realism.
OpenAI is releasing its first artificial intelligence model that runs on chips from semiconductor startup Cerebras Systems Inc., part of a push by the ChatGPT maker to broaden the pool of chipmakers it works with beyond Nvidia Corp.