“4o-image is the first time many people will start to think of the post-reality-filter stage rolling out over the next few years. one’s reality is whatever they want it to be (ghibli or pokemon or lotr or…), and as each human finds that which they truly desire, they then” / X https://x.com/nearcyan/status/1905219687547621740
Roblox’s new AI model can generate 3D objects | The Verge https://www.theverge.com/news/630977/roblox-cube-3d-objects-mesh-ai-text-prompt
“Roblox just casually dropped a app for Cube 3D on Hugging Face generates 3D models directly from text https://x.com/_akhaliq/status/1902882220588605485
“Roblox just dropped Cube 3D: turns your words into instant 3D models! Type “unicorn” = Get a unicorn. Open-source weights & code available on the Hub https://x.com/fdaudens/status/1902710769805897843
“do not sleep on RF-DETR 🔥 it’s a sota, real-time and most importantly, open-source object detector released by @roboflow @skalskip92 my vibe tests on very noisy images and videos have passed 👏 currently being integrated to transformers 🤗 https://x.com/mervenoyann/status/1905318925325173000
Paper page – LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds https://huggingface.co/papers/2503.10625
“Yesterday we published a write-up on RL-based walking We discussed using reinforcement learning, training in simulation, and zero-shot transfer to our robot fleet You can read the article here: https://x.com/adcock_brett/status/1905024472903745765
“Walking around a massive 3d gaussian splat is pretty cool. Game engines and even web apps can give you physics interactions + the beauty of a radiance field. Need to enrich it with more semantic data and other agents to bring this world to life. https://x.com/bilawalsidhu/status/1903652977291768109
“The “metaverse” is a rather empty place without 3d content — generative AI gives us the means to populate it. Here’s a few things that have blown my mind lately — and why I think Roblox might be the perfect sandbox for these primitives coming together. https://x.com/bilawalsidhu/status/1902518941580234891
HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting https://kh129.github.io/hogs/
“WPP, the world’s largest advertising company, is collaborating with NVIDIA, Boston Dynamics, and Canon to explore robotic-assisted cinematography and virtual ad production. Here are some cool shots of Atlas on the set. https://x.com/TheHumanoidHub/status/1903173205155815431
“Vibe creating a 3D scene in Blender got even easier. Just provide a 2D reference image — LLM deconstructs the scene, figures out what 3D assets are needed, generates them using Tripo, and arranges them to match your reference image. Pretty darn cool! https://x.com/bilawalsidhu/status/1904207288291742144
“🎥 Just tested Stability AI’s Stable Virtual Camera – it turns a single photo into dynamic video with AI-powered camera movements! From static meeting room to cinematic sweeps. 🚀 https://x.com/fdaudens/status/1903097771994800547
SynCity: Training-Free Generation of 3D Worlds https://research.paulengstler.com/syncity
“📈 Arena Trend Update (Oct ’24 – Mar ’25) The past month saw a tight race at the top between @xAI and @OpenAI — and this week, a new shift! 😮 @GoogleDeepMind released Gemini 2.5 Pro and it pushed the Arena scoreboard to new highs 📈 #aitrends animation credit: Peter Gostev https://x.com/lmarena_ai/status/1905308013663281176
“334 photos w/ Sony A7III –> 3D Gaussian Splat Seeing reality materialize right in front of your eyes just doesn’t get old — esp when you do the training locally in a tool like PostShot. https://x.com/bilawalsidhu/status/1902950175716303315
HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation https://kkakkkka.github.io/HunyuanPortrait/
“Physical AI Deep Dive: Robotics Meet Reality NVIDIA’s Multi-Trillion Dollar Vision. Google & Tesla’s Moat. Building World Models & Simulating Reality. 🔗 33 min deep dive: https://x.com/bilawalsidhu/status/1903880596654567863
“Just imagine when we get native video input & output We’ll be channel surfing realities layered on top of the real world” / X https://x.com/bilawalsidhu/status/1904922477303677379
“ByteDance just announced InfiniteYou available on Hugging Face Flexible Photo Recrafting While Preserving Your Identity https://x.com/_akhaliq/status/1902937194198700280
ByteDance/InfiniteYou · Hugging Face https://huggingface.co/ByteDance/InfiniteYou
“SpatialLM is super cool, but it does NOT work in real time. To make 3D floor plans on the fly use Apple’s Room Plan API — available in the Polycam app. Computer vision that is truly magical — and it does everything locally on your LiDAR enabled iPhone! https://x.com/bilawalsidhu/status/1903446563856285803
