ByteDance has released Helios, a 14-billion-parameter open-weight video generation model that achieves 19.5 frames per second on a single GPU while generating minute-long video clips. The researchers claim this is the first model of its scale to reach near-real-time performance at this duration. Code and model weights are publicly available.
Researchers introduce RealWonder, a real-time video generation system that simulates physical consequences of 3D actions by using physics simulation as an intermediate representation. The system generates 480x832 resolution videos at 13.2 FPS from a single image, handling rigid objects, deformable bodies, fluids, and granular materials.
Google is expanding NotebookLM's video generation capabilities with Cinematic Video Overviews, which produce styled visual narratives beyond simple slide presentations. The update also includes upgrades to Canvas in AI Mode, enhancing the tool's ability to synthesize and present document insights.
Researchers have introduced PERSIST, a new world model paradigm that explicitly represents 3D environment state rather than learning 3D consistency implicitly from video data. The approach maintains persistent spatial memory and geometric consistency across extended generation horizons, addressing a core limitation of existing interactive video models that lack explicit 3D representations.
Google has upgraded NotebookLM's video overview feature to generate fully animated videos from research notes and documents, moving beyond the previous narrated slideshow format. The new capability uses multiple Google AI models including Gemini 3 and Veo 3 to automatically create visual content that matches the narrative.
Google has rolled out video templates in its Gemini app, enabling users to generate video content more quickly through pre-built starting points. This update follows the introduction of music generation capabilities the previous week.