Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Replicated the laundry task in mujoco web, and also self-trained the RL WBC. By Opus 5.5 in 3 hrs. Agentic real2sim is nearly solved.

Vector Wang

2,492 subscribers

48,049 görüntüleme • 2 gün önce •via X (Twitter)

Sanat Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

35 Yorum

Lindon Gao profil fotoğrafı

Lindon Gao1 gün önce

Wow nice work!

Vector Wang profil fotoğrafı

Vector Wang1 gün önce

Thanks Lindon! Thrilled to get acknowledged by you. I am always fascinated by what Dyna has done.

link profil fotoğrafı

link1 gün önce

@ZeYanjie Cool! How did you trained a urr based rl policy?

Yannis He profil fotoğrafı

Yannis He1 gün önce

forwarded to our eng 🫡

Saket Tiwari profil fotoğrafı

Saket Tiwari2 gün önce

awesome! does mujoco web support cloth folding in sim?

Vector Wang profil fotoğrafı

Vector Wang2 gün önce

Mujoco supports cloth simulation, but the performance is not good and can't really do real-time in web. So in the video the cloth is only presented as rigid body.

Leo profil fotoğrafı

Leo2 gün önce

Did the three-hour build match how the towels behave, or mainly the robot and laundry room?

Vector Wang profil fotoğrafı

Vector Wang2 gün önce

Mujoco supports cloth simulation, but the performance is not good and can't really do real-time in web. So in the video the cloth is only presented as rigid body.

Paolo AI profil fotoğrafı

Paolo AI2 gün önce

@ttktjmt let's add this to MjSwan ?

Tim profil fotoğrafı

Tim2 gün önce

Wow very impressive, I will look into that 🔥

Tony Rick profil fotoğrafı

Tony Rick1 gün önce

laundry task in 3 hrs with opus is kinda nuts

Sergey profil fotoğrafı

Sergey1 gün önce

Very cool, mindblowing what coding agents are capable of.

Ignacio López-Francos profil fotoğrafı

Ignacio López-Francos1 gün önce

This is very cool

Feng Gao profil fotoğrafı

Feng Gao2 gün önce

Was the whole simulation also replicated by Opus 5.5?

Vector Wang profil fotoğrafı

Vector Wang2 gün önce

The robot trajectory is retrieved from official website (only kinematic) and Opus did the scene and robot dynamics to match this trajectory.

Haitong Wang profil fotoğrafı

Haitong Wang1 gün önce

This is so cool. Are the towels modeled as well in sim?

Vector Wang profil fotoğrafı

Vector Wang1 gün önce

Currently all rigid bodies so it's easier to run on web.

Chad L. profil fotoğrafı

Chad L.2 gün önce

super cool!

Jakie PLA profil fotoğrafı

Jakie PLA1 gün önce

3 hours? I could not help myself. This wants to live on a factory cart. Print brackets, bolt on wheels, and let Opus do the boring RL tuning. OH YES.

Max Riazantsev profil fotoğrafı

Max Riazantsev1 gün önce

That looks great! Are you going to try the same with XLeRobot? It is cheap enough to actually test sim-to-real on the real hardware

Brian Zheng profil fotoğrafı

Brian Zheng1 gün önce

Hi will you release the codebase

Alexander profil fotoğrafı

Alexander1 gün önce

is this mujoco? the rendering quality look really high?

Vector Wang profil fotoğrafı

Vector Wang1 gün önce

Mujoco web, so I can have additional renders customized (while still runs in real time in the browser)

Alexander profil fotoğrafı

Alexander1 gün önce

what additional renders? how are you doing that

Vector Wang profil fotoğrafı

Vector Wang1 gün önce

Basically I pre-baked the lighting using blender first.

Greyyy profil fotoğrafı

Greyyy2 gün önce

The rigid-cloth clarification is useful. Which physical properties were estimated from the source assets, and which used defaults? A sensitivity sweep on friction and inertia would be interesting before treating this as a faithful dynamics model.

Jerry Chéng profil fotoğrafı

Jerry Chéng2 gün önce

Wow this is insane! Did the real2sim modeled the robot as well? Would be great if you can share the harness - I have been trying lately as well

Vector Wang profil fotoğrafı

Vector Wang2 gün önce

Robot file is extracted from Dyna's website and added physical properties, and also generated collision mesh. Didn't use special designed harness, just prompted my requirements in claude code.

Jerry Chéng profil fotoğrafı

Jerry Chéng2 gün önce

That's sooo brilliant! Love the idea - and still amazed by the real2sim abilities, agentic robotics is here

刘海若（Hairuo Liu） profil fotoğrafı

刘海若（Hairuo Liu）2 gün önce

will it be open-sourced?

Vector Wang profil fotoğrafı

Vector Wang2 gün önce

After I confirm with Dyna, it’s their IP after all

xard profil fotoğrafı

xard1 gün önce

again it needs to be proved effective when deployed in real world!

newuhe profil fotoğrafı

newuhe1 gün önce

Nice work！How do you generate URR data？

Vector Wang profil fotoğrafı

Vector Wang1 gün önce

~98% synthetic (random keyframes + min-jerk + step targets → FK), seeded by ~97 s of Dyna's public ego-replay clips

rozgo profil fotoğrafı

rozgo1 gün önce

This looks really good. Nice work.

Benzer Videolar

Is Opus 5.5 better than GPT-6 Astra at Physical Intelligence "literally" ? put GPT-6 Astra and Claude Opus 5.5 in two Unitree G1s in MuJoCo Ring Fence. Every 2 sim seconds: state → LLM → joint targets → act. Goal: force the other out of the ring, and Astra won after 31 second.

Is Opus 5.5 better than GPT-6 Astra at Physical Intelligence "literally" ? put GPT-6 Astra and Claude Opus 5.5 in two Unitree G1s in MuJoCo Ring Fence. Every 2 sim seconds: state → LLM → joint targets → act. Goal: force the other out of the ring, and Astra won after 31 second.

Jiafei Duan

54,246 görüntüleme • 21 gün önce

We gave Sonnet 5.5, Haiku 5.5 and Opus 5.5 the same task in Motion: “Make a motion design video about Claude.” Here’s what each one made 👇

We gave Sonnet 5.5, Haiku 5.5 and Opus 5.5 the same task in Motion: “Make a motion design video about Claude.” Here’s what each one made 👇

Motion

71,305 görüntüleme • 6 gün önce

🚀 Anthropic's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and Visual Studio Code.

🚀 Anthropic's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and Visual Studio Code.

GitHub

123,922 görüntüleme • 22 gün önce

I asked Opus 5.5 to make a game inspired by the discovery of the first computer, the Antikythera mechanism. Everything you see and hear is procedurally generated in real time, from code by Opus 5.5. It's a single 3 MB HTML file. Playable Claude artifact below.

I asked Opus 5.5 to make a game inspired by the discovery of the first computer, the Antikythera mechanism. Everything you see and hear is procedurally generated in real time, from code by Opus 5.5. It's a single 3 MB HTML file. Playable Claude artifact below.

edwin

394,747 görüntüleme • 22 gün önce

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Jev + Opus 5.5, side by side. same agent. same task. same 60 decisions. Opus-only: $2.24 - 3m 37s Jev + Opus: $0.43 - 1m 15s the difference is who makes the small calls: which tool runs next - Jev is this output good enough - Jev is the goal met - Jev rewrite the refund handler - Opus 57 of 60 decisions never touched Opus. what you're watching: left routes every decision through Opus 5.5. right asks Jev first, Opus only fires when the task needs real reasoning. per decision: $0.032 -> $0.00025. watch the cost counters, not the output. the output is identical. full setup in the post below ↓

Mahax

19,565 görüntüleme • 16 gün önce

Trained in dingsim. And blue is the same policy but piloting a robot using HF's shipped mujoco simulator. Sim2sim transfer, trained in my Sota rigid body simulator. Trained in under 2 minutes on one 4090 Kneel

Trained in dingsim. And blue is the same policy but piloting a robot using HF's shipped mujoco simulator. Sim2sim transfer, trained in my Sota rigid body simulator. Trained in under 2 minutes on one 4090 Kneel

kache

23,485 görüntüleme • 1 ay önce

Everything in this city is procedural and endless. Running in a browser. WebGPU. 100% code (by Opus 5.5)

Everything in this city is procedural and endless. Running in a browser. WebGPU. 100% code (by Opus 5.5)

Ryan Sael

700,596 görüntüleme • 6 gün önce

Really excited to release mjviser, a web-based MuJoCo viewer, powered by Viser. It has almost all the features of the native MuJoCo viewer, but runs in your browser. Load and simulate any MuJoCo model with a single uv command 👇 uvx mjviser

Really excited to release mjviser, a web-based MuJoCo viewer, powered by Viser. It has almost all the features of the native MuJoCo viewer, but runs in your browser. Load and simulate any MuJoCo model with a single uv command 👇 uvx mjviser

Kevin Zakka

22,902 görüntüleme • 6 ay önce

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Bridgebench

55,327 görüntüleme • 22 gün önce

My vid on Opus 5.5 and GPT 6.1 Sol: - Sol 6.1 is miles better than 6.0, it's worth trying out & the price is nuts - Opus 5.5 is the best Claude model in a very long time

My vid on Opus 5.5 and GPT 6.1 Sol: - Sol 6.1 is miles better than 6.0, it's worth trying out & the price is nuts - Opus 5.5 is the best Claude model in a very long time

Ben Davis

20,050 görüntüleme • 12 gün önce

Sonnet 5.5 basically Opus 5.5 but 50% cheaper and much faster. I've been early testing it and it's incredible. If this is pacing the frontier, sign me up. Demos down below 👇 3D simulation is solved:

Sonnet 5.5 basically Opus 5.5 but 50% cheaper and much faster. I've been early testing it and it's incredible. If this is pacing the frontier, sign me up. Demos down below 👇 3D simulation is solved:

Matthew Berman

281,566 görüntüleme • 16 gün önce

🚀 Claude Opus 5.5 is now available in VS Code with GitHub Copilot. Built for agentic coding, long-running tasks, and knowledge work. Give it a try today!

🚀 Claude Opus 5.5 is now available in VS Code with GitHub Copilot. Built for agentic coding, long-running tasks, and knowledge work. Give it a try today!

Visual Studio Code

76,120 görüntüleme • 22 gün önce

Opus 5.5 is the best model in the world. Full breakdown with special guest Thariq

Opus 5.5 is the best model in the world. Full breakdown with special guest Thariq

Matthew Berman

24,934 görüntüleme • 22 gün önce

Opus 5.5 beats Jev and GPT-6 Sol in 3 moves: Rubik’s Cube race We made 4 models run with same limits for all: 20 moves or 5 minutes. Every move = 1 API call. Results: Opus 5.5: solved in 1m 12.87s with the perfect 3 moves GPT-6 Sol: wrong first move, out of time after 4 moves Jev: 20 moves in 20 seconds, ran out of moves Laya: 20 moves in 9.5s, ran out of moves Opus, GPT, and Jev ran via Laya ran locally.

Opus 5.5 beats Jev and GPT-6 Sol in 3 moves: Rubik’s Cube race We made 4 models run with same limits for all: 20 moves or 5 minutes. Every move = 1 API call. Results: Opus 5.5: solved in 1m 12.87s with the perfect 3 moves GPT-6 Sol: wrong first move, out of time after 4 moves Jev: 20 moves in 20 seconds, ran out of moves Laya: 20 moves in 9.5s, ran out of moves Opus, GPT, and Jev ran via Laya ran locally.

AI/ML API

385,681 görüntüleme • 19 gün önce

Using Fable 5 to add fur and a new voice to my RL creature. The voice is based on the neural network activation (pictured top left). Made with Three.js WebGL / WebGPU Runpod trained with JAX and MuJoCo from Google DeepMind

Using Fable 5 to add fur and a new voice to my RL creature. The voice is based on the neural network activation (pictured top left). Made with Three.js WebGL / WebGPU Runpod trained with JAX and MuJoCo from Google DeepMind

Aaron Lemke

187,855 görüntüleme • 3 ay önce

Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus. /agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.

Introducing Exa Agent: frontier web research at less than half the cost of GPT 5.5 and Opus. /agent orchestrates a mixture of cost-effective models to complete any web research task, from simple data enrichments to building gigantic lists.

Exa

1,074,567 görüntüleme • 4 ay önce

I asked Claude Opus 5.5 to make me an aquarium in Three.js in the style of the legendary aquascaper Takashi Amano. 3d graphics are now a solved issue. It even added Amano Shrimp!

I asked Claude Opus 5.5 to make me an aquarium in Three.js in the style of the legendary aquascaper Takashi Amano. 3d graphics are now a solved issue. It even added Amano Shrimp!

Alix Ollivier

38,735 görüntüleme • 19 gün önce

Claude Opus 5.5 + Higgsfiled built this animated windmill in Blender in 15 minutes. The modeling, rigging, texturing and animation – all made by AI.

Claude Opus 5.5 + Higgsfiled built this animated windmill in Blender in 15 minutes. The modeling, rigging, texturing and animation – all made by AI.

Higgsfield AI 🧩

52,259 görüntüleme • 22 gün önce

JEV + Opus 5.5 is insane for live design... I built a live site redesigner with JEV + Opus 5.5 Paste any link → press Start → scroll, and Jev + Opus 5.5 rebuild every section of the site in front of you Full production ship in 20 seconds: 1. IntersectionObserver fires when a section is 30%+ in the viewport 2. Jev returns one typed decision in ~0.1s: { layout, copy, drop, type, palette, p } 3. Opus 5.5 writes the component (TSX) + a CSS patch for the chosen style 4. The new section wipes in with clip-path, the old one blurs out 5. Next section enters the queue, one at a time, no race conditions Output: 8 sections of a 2015 hosting site rebuilt in ~20s, streamed line by line in the terminal 3 styles, one renderer: orthographic globe + lambert shading → ASCII / 2-color halftone / ink stipple Scroll yourself and it redesigns whatever you land on Jev decides fast, Opus designs it

JEV + Opus 5.5 is insane for live design... I built a live site redesigner with JEV + Opus 5.5 Paste any link → press Start → scroll, and Jev + Opus 5.5 rebuild every section of the site in front of you Full production ship in 20 seconds: 1. IntersectionObserver fires when a section is 30%+ in the viewport 2. Jev returns one typed decision in ~0.1s: { layout, copy, drop, type, palette, p } 3. Opus 5.5 writes the component (TSX) + a CSS patch for the chosen style 4. The new section wipes in with clip-path, the old one blurs out 5. Next section enters the queue, one at a time, no race conditions Output: 8 sections of a 2015 hosting site rebuilt in ~20s, streamed line by line in the terminal 3 styles, one renderer: orthographic globe + lambert shading → ASCII / 2-color halftone / ink stipple Scroll yourself and it redesigns whatever you land on Jev decides fast, Opus designs it

Movez

107,322 görüntüleme • 20 gün önce