ByteDance launched SeedRealtime, a full-duplex audio-video model for real-time AI interaction. Unlike Seedance (long-form video generation), this is conversational AI that listens and speaks at the same time—with live video input.
1 h ago 5 6
The Seed team pushes single-shot generation to 30 seconds, with multi-modal references (30 images + 10 videos + 10 audios) and timestamp editing.
Aug 2, 2026 at 15:16 8 11
MiniMax releases H3, an open-source full-modal (text, image, audio, video) model at one-third the price of competitors. The AI video market stops being binary: expensive closed-source or weak open-source.
Jul 31, 2026 at 12:50 12 14
DeepMind's ER 2 update pushes embodied reasoning toward video understanding and fleet-level coordination - the embodied-foundation race gets its Google-branded milestone.
Jul 30, 2026 at 19:40 13 14
Black Forest Labs releases FLUX 3, its new generation of multimodal flow matching models. The lab claims superior results to Seedance 2.0 and Gemini on internal benchmarks. It remains to be confirmed by third-party evaluations.
Jul 24, 2026 at 21:00 8 8
BFL claims a state-of-the-art shift against Seedance 2.0, Gemini Omni, and Grok Imagine - and in turn pushes a "video-action" derivative for robotics.
Jul 24, 2026 at 09:33 9 8
The Philippines publicly denounce a Chinese state media AI-generated video as racist. Generative video moves from marketing to diplomacy.
Jul 19, 2026 at 00:37 8 8
After the wave of teasers and benchmark videos, Moonshot AI has put Kimi K3 into production on kimi.com and via its code API. The question is no longer "when," but "at what price, at what latency, and for what real use."
Jul 16, 2026 at 21:46 29 8
The China humanoid pack is now shipping demos at Silicon Valley pace. The signal isn't a video - it's the cadence.
Jul 16, 2026 at 13:50 6 11
Benchmark clips are everywhere. The model card, the API, and any reproducible evaluation are not.
Jul 16, 2026 at 13:50 32 8
