World models aren't the same as regular video models.... The benchmarks are different. I'm really stoked to see what visionary creators do with this technology.show more

make a mech surface texture with COPs ✌️ -... use the texture with different UV scales for the same 2 models - adjust the displacement map heights to overlap 2 models #houdini #copernicus #apexrigshow more

World Models are the path for some AI Models... in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.show more

We’re continuing to see exciting results as we work... with our Meta Movie Gen models, here are some more examples of what they can do 🧵show more

Humanoid Behavior Foundation Models are entering the perception era.... Perceptive BFM shows how vision can adapt the same human motion prior to different terrains instead of assuming the environment is already compatible. Really impressive work!show more

🤖 One predictive backbone, three distinct tasks, consistent gains:... a strong signal that investing in reusable world models is the right abstraction for robot learning. Toyota Research Institute (TRI) just ran the same idea three different ways—and it worked each time. Using our NVIDIA Cosmos Predict 2–style world models, they hit SOTA with dynamic view synthesis, teleop data augmentation (even up against MimicGen as an upper bound), and navigation world models. 🙌 📚 dynamic view synthesis 📚 teleop data augmentation (also compare to MimicGen as an upper bound) 📚 navigation world models 📸 fromshow more

"Oh cool, I'm glad to see you got some... models to help pass the time, what did you get?" My last 2 braincells:show more

Introducing benchmark tracking across all of arXiv With thousands... of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!show more

It's Christmas morning: OpenAI and Anthropic shipped new models... on the same day! We tested GPT 5.3 Codex vs. Opus 4.6 head-to-head. Verdict: the models are converging. Here’s what we found 🧵show more

“Do One” - the first single proper from Undefeated... - OUT NOW. Say what you really think in 2 minutes 20 seconds; it’s not who you are, it’s the things you choose to do. Enjoy the song, the video, get stoked for the album! Full video here:show more

So when are they gonna tell the story about... how unhinged this man really is? It's not just Kat. He does the same shit with the kids. He is the most loving man in the world as long as you're doing what he wants you to do. The moment you don't he snaps like a lunatic #BeyondTheGatesshow more

MiniMax H3 vs Seedance 2.0 on Pollo AI Same... prompt. Two models. Completely different outcomes See the difference for yourself And Seedance 2.5 is coming soon to Pollo AIshow more

Looking for the cutting-edge of AI research? Follow Salesforce... AI Research to see how we're transforming enterprise technology through advanced innovations. From world models to agentic systems, discover the future of AI before it hits the market.show more

Since I'm working on a Topdown/Isometric Adventure-like game for... The Sandbox Studio's #Gamejam - I also needed to fix some issues where when we would walk behind trees, terrain or models, we coudl still see our main character. So, playing around with some 'fade/dither' effect to do that. Also, made some changes of the visual style of the paths, and shadow system + added some extra models in the mix! 🎨 Love vibing with Three.js + The Sandbox Creatorsshow more

New AI video model MotionStream lets you control motion... in real time. This is a glimpse at what all video models will allow you to do in the future.show more

happy Good Friday.. can we get more underwear models... like this all over the world? not asking for much reallyshow more

No matter how much we try, multiple-opponent scenes always... seem to be challenging for AI video models. Let's see if the upcoming Seedance 2.1 / 2.5 next week can finally improve this. What do you think about the petal effect? I'm considering using it in future videos as well. Midjourney + Gpt Image 2 + Seedance 2.0 You can find the prompts in the first reply.show more

Grok has developed a #1 ranking addiction. Grok Voice... Think Fast 1.0 now ranks #1 on the Artificial Analysis τ-Voice benchmark for real-world customer-service resolution. Meanwhile, Grok Imagine Video 1.5 just took the #1 spot on the Video Arena leaderboard. Different models. Different platforms. Same result. The Grok ecosystem is starting to stack trophies. Grok xAIshow more