sony's hawk eye cameras are used for VAR (video assisted referee) which heavily rely on computer vision. but only now is that data feed being explored to surface in replays (which is nuts to me)
MULTIMODAL AI
-
Seedance 2.0 Generates Shaw Brothers Film Style Short Amazing Results
By
–
OMY Is this AI generated!???? https://t.co/LNY3LmSsX3
— Tiezhen WANG (@Xianbao_QIAN) 7 février 2026OMY Is this AI generated!???? Tractor (@tuolaji2024) Made with seedance 2.0, is AI this powerful now? "Blood Blade Demon Cult", created a short film in Shaw Brothers movie style using the latest Seedance 2.0 model. The entire production relied on just one image of the main characters (shown at the end of the video) and one image of the villain character, with AI handling everything else – the editing, audio-visual synchronization, scene transitions all flow seamlessly, and the results are quite impressive. — https://nitter.net/tuolaji2024/status/2020083327907373103#m [Translated from EN to English]
→ View original post on X — @shiqi_yang_147, 2026-02-07 11:51 UTC
-
Genie 3 world model technology successfully applied to Waymo autonomous driving
By
–
We researchers often say "let us build this cool new technology and there will be many ways the company/society can use it, such as <list>". Here's a great example of that happening! Fun to see Genie help Waymo!! Jack Parker-Holder (@jparkerholder) Super excited to see Genie 3 having impact in autonomous driving. We've talked…. a lot… about this type of application for world models, and its been incredible to see the Waymo team do things we previously dreamed of! Congrats @maxjiang93 and team!! — https://nitter.net/jparkerholder/status/2019808695169982887#m
→ View original post on X — @_yutaroyamada, 2026-02-07 02:37 UTC
-
Sora Now Supports Image-to-Video Generation with New Moderation Controls
By
–
Sora now allows generating videos and characters from images of people with stricter moderation. "Starting today, eligible users can upload images with people to make videos in Sora, after attesting that they have consent from people featured and rights to upload the media."
-
Voxtral: Real-time audio streaming to text
By
–
Voxtral can now directly stream audio input into text output. Perfect for:
— Mistral AI for Developers (@MistralDevs) 6 février 2026
– Live subtitles
– Language learning apps
– Note-taking tools
– And more!
Made a demo for you to try directly on hugging face ! pic.twitter.com/kHLqGo41PqVoxtral can now directly stream audio input into text output. Perfect for:
– Live subtitles
– Language learning apps
– Note-taking tools
– And more! Made a demo for you to try directly on Hugging Face! [Translated from EN to English]→ View original post on X — @guillaumelample, 2026-02-06 19:45 UTC
-
Arcturus Uses 4D Gaussian Splatting for Volumetric Sports Video
By
–
This will change the way we experience sports forever — watching the game from a gods eye view.
— Bilawal Sidhu (@bilawalsidhu) 6 février 2026
Arcturus is building 4D gaussian splatting tech that can capture every angle of a sporting event and pushes the bar for volumetric video. I tested this in a headset and it makes 360… pic.twitter.com/YgsDHzoQ21This will change the way we experience sports forever — watching the game from a gods eye view. Arcturus is building 4D gaussian splatting tech that can capture every angle of a sporting event and pushes the bar for volumetric video. I tested this in a headset and it makes 360
-
AI Analyzes Floor Plans and Generates 3D Structures
By
–
AI can analyze floor plans and generate 3D structures, transforming construction and home projects. pic.twitter.com/bcGdXOInUc
— Satya Mallick (@LearnOpenCV) 6 février 2026AI can analyze floor plans and generate 3D structures, transforming construction and home projects.
-
Exploring the OpenAI Image Generation Skill
By
–
Did you try the imagen skill? – in my biased opinion it's much more fun to play with https://
github.com/openai/skills/
blob/main/skills/.curated/imagegen/SKILL.md
… -
Critique of video generation model lacking world model
By
–
C’est de la pure merde. Ca semble pas du tout etre un world model.
— Defend Intelligence (Anis Ayari) (@DFintelligence) 5 février 2026
Mais juste un modèle de génération video image par image avec des « inputs » qui se transforme en prompt pour conditionner une image suivante qui marche quasiement jamais.
Aussi ça ressemble à tout sauf à du… https://t.co/3OCqzUEznvIt's pure crap. It doesn't seem like a world model at all. But just a video generation model frame by frame with "inputs" that turn into a prompt to condition the next image, which almost never works. Also, it looks like anything but real-time. Sure, you gotta start somewhere,
-
Claude Opus 4.6 Advanced AI Model Released by Anthropic
By
–
Claude Opus 4.6 is Anthropic’s most advanced model for professional work and long-running agents. It comes with big gains in reasoning, long-context, tool use, vision and coding. You can try it in Poe app on all platforms and in the Poe API at https://
poe.com/Claude-Opus-4.6