video
A video model counted events correctly two-tenths of one percent of the time News
Asked to count simple events in short synthetic clips, Google's Gemini 3.6 Flash got the final count right 0.2 percent of the time in the hardest setting and recovered only 18 percent of the events that actually occurred.
Vector Quantization: Turning Continuous Data Into a Vocabulary Lesson
Vector quantization forces a neural network's continuous internal representations to snap to a finite set of learned reference vectors, converting images, audio, or video into sequences of discrete symbols that a language model can predict just like words.
Microsoft lets the video codec pick which pixels the model sees News
Microsoft's Mage-VL reuses a video file's own compression decisions to choose which image patches a vision model processes, cutting visual tokens by over 75% and reporting up to a 3.5x speedup over uniform frame sampling.
TimeLens2 teaches video AI to point to the exact seconds that answer a question News
Researchers released TimeLens2, an open-weight video model fine-tuned to answer a text query by returning the exact timestamp intervals in a video that contain the evidence, using a new distance-sensitive reward and a carefully curated dataset, with small versions reported to beat much larger open models on temporal grounding.
One model that listens, sees, and talks back in real time News
Wan-Streamer collapses the usual chain of separate speech and video tools into a single model built for live, two-way conversation.
An open-source 'AI crew' that turns a coding assistant into a video studio News
A project called OpenMontage shot to the top of GitHub in a day, claiming to be the first open-source system that lets AI agents handle a whole video production from script to final cut.
Google DeepMind puts $75 million into film studio A24 to build AI moviemaking tools News
A frontier AI lab is investing in a prestige studio to develop production tools hands-on with filmmakers -- officially not a deal to train models on A24's films.
Robots may not need to picture the future as video to act on it News
Generating a full imagined video of what comes next is expensive. A new method skips it — pulling a robot's next move straight from the inner workings of an image-editing model.
AI 'world models' have short-term memory — they forget what's off-screen News
A sweeping study of dozens of AI video-prediction systems finds they don't truly remember the world; when something leaves the frame, they quietly reinvent it the next time you look.
VideoChat3-4B Tool
A fully open 4B-parameter video multimodal model for general, long-form, and streaming video understanding, released with weights, training code, training strategy, and datasets.
OpenMontage Tool
An open-source system that turns an AI coding assistant into an automated video-production studio, with a large library of pipelines, tools, and agent skills for editing and assembling video.
Mage-VL Tool
Microsoft's codec-native multimodal model that reuses a video file's own bit allocation to pick visual tokens, reporting over 75% fewer tokens and up to 3.5x faster inference than uniform frame sampling. Works with H.264, HEVC and DCVC-RT.
ComfyUI Tool
A visual, node-based studio for generating images and video with open models. Powerful and endlessly extensible.
Claude Video Tool
A /watch skill that downloads a video, extracts adaptive keyframes, pulls existing captions or falls back to Whisper transcription, and hands the material to the host coding agent. An input adapter rather than a planner.