AI Video
Text-to-video generation is one of AI's fastest-moving frontiers: OpenAI's Sora, Google's Veo, Runway, Kling and others turn a couple of sentences into increasingly realistic clips. It is reshaping advertising, film and the debate over authorship and deepfakes. Here is all our coverage of AI video: model releases, quality, pricing and industry shifts.
RealMe Builds 2K Volumetric Video from a Handful of Cameras Using Diffusion
RealMe turns sparse low-resolution captures into 4D-consistent 2K volumetric video, using a video diffusion model and a latent-space frequency loss.
DONIC teaches one policy to control two hands: 86.79% success without fine-tuning
Researchers unveiled DONIC, the first general-purpose tracker for two dexterous hands. A single checkpoint hits 86.79% success on new trajectories and 57.32% on…
NUS Teaches a Model to Find What It Described: gIoU Rises From 57.5% to 68.2%
Generalized CycleGRPO links describing a region and finding it from text in a single RL loop, with no reference captions and no LLM judge. On GroundingSuite, gIoU…
Black Forest Labs: A 70-Person Team Takes On Silicon Valley's Giants
OpenAI Unveils New ChatGPT Voice Powered by GPT Live, With No Technical Details
EgoX Merges Camera, Hands and Objects Into One 3D Scene, With 65.6% Lower Hand Error
Stateful Harness Lifts World Model Accuracy on Hidden State from 32% to 92%
SpatialScout: Best VLM Agent Builds Only 41.71% of a Room's 3D Map
The new SpatialScout benchmark tests whether VLM agents can explore scenes on their own and map objects. Claude Opus 5.5 scored 41.71%, and only 3.25% of targets…
Omni-Woodpecker Cuts Hallucinations in Omni-LLMs Without Retraining: +12.9 on CMM
A Nanjing University team proposes OWP, a method that corrects an omni model's hidden states before decoding and adds 12.9 points on CMM for Qwen2.5-Omni-7B.
Four Chinese Players Are Building Real-Time Interactive Video Worlds
Fine-Tuning Gemma 4 with GPUs on Cloud Run: From 89% to 94% in Animal Classification
Stanford Online Posts Lecture 12 of AA274A: Classical Computer Vision for Robots
Why Multimodal Models Can't See Web Interfaces
OpenAI shows how an engineer's dot triaged a night-time incident and launched Codex
In an OpenAI video, engineer Ali hands an on-call incident to his dot at 3 a.m. The dot opens a thread in Codex, and Ali steers the fixes from his phone through…
Robots learn from 20 854 hours of video: how Sharpa is building dexterous manipulation
Robotics data is moving from costly teleoperation to human video: EgoScale used 20 854 hours. Here is how Sharpa fits its system into that logic.