AI Briefing#video-generation
The latest AI and developer news about #video-generation, with the original source and a short summary.
The latest AI and developer news about #video-generation, with the original source and a short summary.
Bidirectional diffusion models estimate rollout errors using forward-backward round-trip discrepancies.
MiniMax has released the weights for its 33B H3 model, which jointly generates video and stereo audio, but Korea is excluded from the license.
Seedance 2.5 has launched with enhanced 30-second generation and multimodal reference and precise editing capabilities.
xAI unveiled Imagine Video 1.5, which supports voice and image references along with native 1080p.
MiniMax H3 has been added to AI Gateway, supporting 2K resolution video generation through text and multimodal inputs.
Parallel Decoding Distillation predicts multiple denoising steps at once to improve the speed and diversity of video generation.
Nvidia has announced SANA-Video 2.0, which accelerates high-resolution long-form video generation through hybrid attention technology.
Vidu S1, an interactive video model that responds in real time to users' voice instructions and generates video indefinitely, has been unveiled.
CalibAtt is a technique that speeds up video generation models by up to 1.58x by identifying unnecessary connections during attention computation.
Decart has launched Lucy 2.5, a real-time AI model that can remove objects and replace backgrounds in video using natural language prompts.
The RTCA workshop at NeurIPS 2026, covering research on real-time multimodal conversational agents, has opened its call for papers.
GenCeption is proposed as a general-purpose vision model that performs diverse visual cognition tasks by leveraging video generation models.
Wan-Dancer, a model that generates high-quality dance videos over 1 minute long in sync with music rhythm, has been released.
VideoFlexTok dramatically improves training efficiency and generation length by representing video in stages, from abstract information to fine details.
Google has added Gemini Omni Flash, a high-performance video generation model, and Nano Banana 2 Lite, an ultra-fast image model, to the Gemini Enterprise Agent Platform.
Seedance 2.5 extends video generation length to 30 seconds, supports 50 multimodal references, and supports 4K resolution.
A model and dataset called MolmoMotion have been released that predict the future 3D trajectory of objects based on language instructions.
xAI's **Grok Imagine Video 1.5** has launched on **AI Gateway**, enabling video generation with audio synchronized to images.
Google unveiled the video generation model Gemini Omni and Gemini 3.5 Flash with enhanced agentic capabilities.
ByteDance has unveiled Lance, a 3B-scale unified multimodal model that supports understanding, generation, and editing of images and videos.
The open-source audio-driven human video generation framework LongCat-Video-Avatar 1.5 has been released.
Google has launched an AI avatar tool within Gemini that creates digital replicas using a person's own voice and video.
ByteDance has open-sourced a 3B-scale multimodal model with image, video, editing, and reasoning capabilities.
A self-hosted open-source tool that uses AI to analyze long-form videos and automatically convert them into viral shorts has been released