🔥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

🚀 Introducing #SparseVideoGen: 2x speedup in video generation with HunyuanVideo with high pixel-level fidelity (PSNR = 29)! No training is required, no perceptible difference to the human eye! Blog: svg-project.github.io Paper: arxiv.org/abs/2502.01776 Code:

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy)

Humanoids need to perceive the environment in the real world Using 4D reconstruction techniques, we turn casual human videos into training data for an environment-aware humanoid policy Super excited to share: VideoMimic.net

Excited to introduce PyRoki ("Python Robot Kinematics"): easier IK, trajectory optimization, motion retargeting... with an open-source toolkit on both CPU and GPU

Tired of teleoperating your robots? We built a way to scale robot datasets without teleop, dynamic simulation, or even robot hardware. Just one smartphone scan + one human hand demo video → thousands of diverse robot trajectories. Trainable by diffusion policy and VLA models

Very impressive! At VideoMimic.net, we already: learn from 3rd-person human videos + RL -- for locomotion. Excited to see where this path goes next!

Ever wish you could turn your video generator into a controllable physics simulator? We're thrilled to introduce Force Prompting! Animate any image with physical forces and get fine-grained control, without needing any physics simulator or 3D assets at inference. 🧵(1/n)

Bored of linear recurrent memories (e.g., linear attention) and want a scalable, nonlinear alternative? Our new paper “Test-Time Training Done Right” propose LaCT (Large Chunk Test-Time Training) — a highly efficient, massively scalable nonlinear memory with: 💡 Pure PyTorch

✨New preprint: Dual-Process Image Generation! We distill *feedback from a VLM* into *feed-forward image generation*, at inference time. The result is flexible control: parameterize tasks as multimodal inputs, visually inspect the images with the VLM, and update the generator.🧵

Cudos to VideoMimic team:)

Q-learning is not yet scalable seohong.me/blog/q-learnin… I wrote a blog post about my thoughts on scalable RL algorithms. To be clear, I'm still highly optimistic about off-policy RL and Q-learning! I just think we haven't found the right solution yet (the post discusses why).

FlowMo, our paper on diffusion autoencoders for image tokenization, has been accepted to #ICCV2025! See you in Hawaii! 🏄‍♂️

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to

For everyone interested in precise 📷camera control 📷 in transformers [e.g., video / world model etc] Stop settling for Plücker raymaps -- use camera-aware relative PE in your attention layers, like RoPE (for LLMs) but for cameras! Paper & code: liruilong.cn/prope/

Excited to share Flow Matching Policy Gradients: expressive RL policies trained from rewards using flow matching. It’s an easy, drop-in replacement for Gaussian PPO on control tasks.

🤖 Initial code release is up for VideoMimic Real2Sim! github.com/hongsukchoi/Vi… VideoMimic is a real-to-sim-to-real pipeline for deploying humanoids in the real world. It supports: - Human motion capture from video - Environment reconstruction for simulation from video -

Huge shout out to Viser!! It made all my 3D/4D related projects so much more easier. Thank you, Brent Yi!!🥹