Wow, my first post to hit 2k likes! 🥹 Thank you all so much!!🥹 Really happy to see Motion2MixamoRig pass 200 stars on GitHub too! ⭐️ I've noticed a lot of new people following me after that post, so I thought it'd be nice to reintroduce myself: I'm a software engineer based in Shenzhen, China. During the day, I build software for medical devices. Outside of work, I explore Autonomous AI4S and robotics. I'll mostly post about what I'm building, what I wanna find out, and sometimes life in Shenzhen. Anyway, feel free to hit me up! Always down to chat or build something together :)

We found a way to scale humanoid control that reduces GPU-hours by more than 1000×. Across 129,514 motions, SuperMimic surpasses the state of the art (128 GPUs, 7 days) with 1 GPU in 3 hours. Project: supermimic.github.io Demo: supermimic.github.io/demo/

🌍Meet our World2HOSI: 3D Gaussian scenes + text → long-horizon human–object–scene interactions. Existing motion experts collaborate through a shared, evolving world—without training a new unified motion generator. nintreesssss.github.io/World…

너무 귀여워🥹

现在越给机器人姿态调参我感觉我应该去学一些机械物理。。。

机器人的「ChatGPT」时刻来了！！！ 前英伟达 GEAR 团队出来创业的 Dream Labs 刚才正式发布了 Dream-1 模型 不用你的机器人数据，不用微调，不用懂机器学习。只要是双臂加平行夹爪的机器人，接上就能零样本控制。 跨机器人实现原理： · 主要是靠视频推测机器人下一步怎么动 · 输出主要是夹爪的位置和开合，，再交给机器人自己的逆运动学去计算，所以不同的机器人能共用一套动作 · 摄像头要有三个，头部一个，左右手腕各一个

Motion2MixamoRig + @fal Flux 3 Max = real-time high quality text to animation!

That's what's so appealing about the open-source project.

Cooking Motion2MixamoRig v0.1.X

Unitree Introducing: UniUni Intelligent Swarm Control System🎉 It enables rapid, intelligent choreography of swarm robot movements and formations, real-time device status monitoring, safety braking, and more. How many robots would you like to see perform together?

The first AI robot to ring the bell on Nasdaq

不是哥们，这特么也太猛了！ 把一段跳舞视频直接变成 3D 角色动画！🕺 Motion2MixamoRig：单人视频（甚至一张照片）→ 自动提取人体动作 → 重定向到任意 Mixamo 角色，直接输出能进 Blender / Unity 的 .glb。 开源：github.com/MaxLiu22/Motion2M…

I used to work in 'deep tech' hardware and one of the ideas that has been kicking around my head for a decade is the joint co-evolution of all the individual parts of a mechatronic system in simulation and then benchmarked with rapid prototyping. this idea isn't novel, but I think all the pieces are there to do it better than ever today with compliant materials and passive dynamics - storing energy in flexible components and releasing it at the right time, getting us much closer to the comparatively energy efficient, quiet and safe motion that we expect of biological kinematics.

@DynaRobotics 's Taku rang the bell at @Nasdaq today 🔔 🦾

NVIDIA just dropped an open source Apache-2.0 licensed CAD kernel HAHAHAHAHAHAHAHAHAHAHA i honestly feel bad for the prop CAD bros. this week has been nonstop L's and it isn't getting better from here github.com/NVIDIA-Omniverse/…

Good stuff👍

30 minutes. One take. No cuts. We put Natura-1’s zero-shot generalization to the test with complex spoken instructions and unfamiliar tasks and environments. It responds to new requests, adjusts and retries when an action fails, and keeps going autonomously.

We collaborated with @scaleAI to build a high-fidelity port simulation RL environment where AI agents tackle real-world logistics challenges

Free Open-Source Video-to-Animation for Mixamo Rigs, Now Inside Blender Motion2MixamoRig copies the motion of a person in a video onto a Mixamo-rigged character and hands you a skinned GLB for Blender or Unity. Highlights: • Video or a single photo as input • New Blender 4.2+ extension panel • Runs locally on CPU, CUDA or Apple Silicon • Reuse one take on other characters in tens of seconds • Apache-2.0 code GitHub: github.com/MaxLiu22/Motion2M…

Using large-scale GPU parallelized reinforcement learning in Isaac Sim, we are able to obtain a robust whole-body controller for Taku optimized for precise loco-manipulation.

Teleoperating two Ability Hands with @ManusMeta gloves on @AgilexRobotics Nero arms 🦾🦾 Hand and arm data streams into a full 3D sim synced to a depth camera, all built with @claudeai. Real to sim data that can train models to run these tasks autonomously. Boom 💥