🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I’m pleased to share a detailed blog on Feature-based vs. GAN-based Learning from Demonstrations: When and Why. This article provides valuable insights for those looking to scale RL systems using offline reference data, especially in the context of physics-based agent control.

Just tried out AnyCoder on Hugging Face — A very cool AI tool that lets you build applications just by describing them in everyday language. Great for quick prototyping! huggingface.co/spaces/akhaliq… Nice work! AK #AI #WebDev #Prototyping #AnyCoder

Based on our past experience in text-to-motion (T2M) generation, we’ve come to appreciate just how critical high-quality textual descriptions are for generating semantically accurate motion... SnapMoGen now aims to tackle this challenge with richer and more expressive annotations

🎉 Today at Decart we're announcing Mirage. The first generative video model that runs in real-time, to infinity. Mirage is a Live Stream Diffusion (LSD), a breakthrough that transforms any video into anything you can imagine, as it plays. 🎮 Try it: mirage.decart.ai

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound

#geogram + #graphite + #blender Python scripting = robust CSG directly available in Blender ! Everything is a numpy array.

🌊 New AI system for designing autonomous underwater gliders - from concept to fabrication in record time. ✅ Fast shape optimization ✅ Efficient CFD modeling ✅ Real-world validation 🎥 youtube.com/watch?v=hpzakp…📖 news.mit.edu/2025/ai-shapes… #AI #OceanTech

🚶Human motions have become popular in guiding RL training and making robots walk like real human. 🤖 🚀 Excited to share our latest research on recent advances in this technology, with a guideline on the best practices! 🔗breadli428.github.io/post/lfd/ 📄PDF: arxiv.org/pdf/2507.05906

"Generate in Parts" is so insanely good, it even generated the bullets inside the cylinder - automatically, from a single image. Every part comes cleanly separated: barrel, cylinder, trigger, hammer, etc… The future of 3D AI goes live next week on app.scenario.com 🔥

Contact. Contact. Contact. For spatial intelligence, this is what location, location, location is in real estate. InteractVLM predicts 3D contacts on humans and objects from a single image. This is a key step in training machines to interact with the 3D world.

Our online book Physics-Based Simulation v1.0.2 is live! phys-sim-book.github.io New in this update: ABD, modal reduction, MPM, PBD, and linear solvers! Huge thanks to all the amazing contributors who made this happen!

I'll be presenting our new predictive simulation model at ISB 2025 in Stockholm next week! Parallel session 9F (Movement Generation and Prediction), Wednesday July 30 from 10:40 to 12:00. Hope to meet you there!

Extremely happy to share our paper got accepted to IEEE RAS Transactions on Robotics (T-RO)! We focuses on one thing that is truly important but often ignored - motion retargeting! This is truly one step towards leveraging motion data on legged robots.

Check out “PDT: Point Distribution Transformation with Diffusion Models”, to appear at #SIGGRAPH2025. PDT studies the use of diffusion models for modeling structural priors through point distribution transformations, enabling applications in remeshing, skeleton extraction, and