Linzhan Mou

Ph.D. student @PrincetonCS. Intern @Meta.

[Linzhan Mou @LinzhanMou]

🪄 Bring your 3D characters to life with words!

Introducing UniMate: one unified model for text-driven animation across diverse skeletons—from humans and animals to articulated objects.

🎬 A rigged asset + a text prompt → motion.
No per-skeleton retraining needed!

🌐 https://t.co/4dkns5mr88

[Linzhan Mou @LinzhanMou]

@nazimadakli Agreed. Distilling agent-generated data into an expert model looks promising, and that model would be far cheaper and faster to run.

[Linzhan Mou @LinzhanMou]

@dranben Thanks for trying it! UniMate is an early step toward text-to-animation for any skeleton. Part of its capacity goes into handling different topologies, so it still trails specialized models on human motion. We plan to close that gap with more data.

[Linzhan Mou @LinzhanMou]

@imost @GokulEpiphany Several of the open-source auto-riggers seem pretty good. SkinTokens is an improved version of UniRig, but I haven't tried it yet.

[Linzhan Mou @LinzhanMou]

🪄 Bring your 3D characters to life with words!

Introducing UniMate: one unified model for text-driven animation across diverse skeletons—from humans and animals to articulated objects.

🎬 A rigged asset + a text prompt → motion.
No per-skeleton retraining needed!

🌐 https://t.co/4dkns5mr88

[Linzhan Mou @LinzhanMou]

@nazimadakli @rahul__gh0sh Thanks for giving it a try! Agreed, agentic approaches handle this better right now. Our data is still limited, which shows. If you can share some of your outputs, that would really help us improve.

[Linzhan Mou @LinzhanMou]

@rahul__gh0sh @nazimadakli Nice work on the cost side! I think agentic systems also work well as a final refinement stage: let a motion diffusion model generate the base motion, then have the agent fix the details (contacts, constraints, timing). That might help with the more complex animations too.

[Linzhan Mou @LinzhanMou]

@DynaRobotics Super cool agentic robo system for long-horizon task!

[Linzhan Mou @LinzhanMou]

@RisingSunInt_ Yes, with motion expansion you can chain prompts, and each segment continues from the end of the last one. That gives you seamless walks of any length without snapping.

[Zhiyang (Frank) Dou @frankzydou]

Over the past few weeks, GPT-6 Astra, Claude Code with Opus 5.5, and other recent foundation models have surprised many of us in graphics, CAD, and robotics. They can now work directly with Blender, CAD kernels, game engines, physics simulators, and real robots very well. New examples appear almost daily, faster than the publication cycle can capture.

📝To keep track, we maintain a Living Survey of frontier AI for Design & 3D Modeling & Robotics:
🌐 https://t.co/irJ9uUvdh2

Currently, it organizes 243 cases from 345+ public showcases and developer reports across 3D modeling, CAD and industrial design, animation, simulation, and robot control, each linked to its original source.

(If you are working on related projects, it's better to check this out: )

Different from a traditional survey, three ideas guide it:

1. Horizon scanning beyond publication lag
In an era where frontier foundation model capabilities evolve rapidly, traditional academic publishing cycles could lag behind public community developments and empirical findings. This platform establishes a centralized, high-velocity empirical synthesis repository to provide researchers and engineers with timely visibility into ongoing developments across 3D generation, parametric CAD, and embodied robotics—anchoring these observations in objective evaluations of strategic opportunities and critical safety boundaries.

2. Demonstrations as a distributed record of use
We analyze the corpus of over 345 publicly documented showcases and developer reports as an extensive, distributed "crowdsourced user study." This framing captures how models operate when prompted across diverse geometry kernels (CGM, Open CASCADE), DCC software (Blender), physics simulators (Isaac Sim, MuJoCo, Genesis), and physical robot hardware—revealing real-world workflow friction, prompt overhead, and boundary failures that static benchmarks miss.

3. Ranking by open verifiability
A central challenge is balancing the timely collection of rapidly emerging results with the need for high-quality, evidence-based evaluation. Our approach is to rank cases by open verifiability—the amount of evidence that others can directly inspect.

Equally impressive demos can carry very different evidence, so every case is ranked by what others can inspect:
- Rank 1 · Demo + Implementation Code: public code, scripts or CAD/robot harnesses (availability/verifiability)
- Rank 2 · Demo + Interactive Web Link: a live web app, 3D viewer or cloud CAD project
- Rank 3 · Demonstration Media Only: video or screenshots only

Note: Rank 1 means the evidence is inspectable, not necessarily reproducible from a clean setup.

Gallery: https://t.co/Tgo48HU4dH

Contributions are very welcome via pull requests on GitHub. We especially welcome Rank 1 contributions (demos with code) and Rank 2 contributions (demos with interactive webpages).

Many thanks to our collaborators: Jamison Meindl(@meindljamie), Akihisa Watanabe(@Akihisa_Wat ), Anna Deng, Tianyu Huang(@tyanyuy3125), Igor Sadalski(@igorsadalski ), Harrison Liang, Minghao Guo(@GuoMh14 ), Benjamin Tod Jones, Wojciech Matusik(@wojmatusik ).

[Stefan 3D AI @Stefan_3D_AI]

New Open-Source AI Animator: Text-to-Animation for Humans, Animals, Creatures, Robots & More

UniMate generates motion from text prompts for rigged 3D characters. Describe an action and turn it into animation.

Highlights:
• One model, different skeletons—no separate retraining for each rig.
• Generate transitions between existing keyframes.
• Edit motion with text while keeping selected joints unchanged.
• Extend animations with a sequence of prompts.
• Export animated meshes as FBX and GLB.
• MIT-licensed code + downloadable preview weights.

https://t.co/iy9zRxWfep

[Linzhan Mou @LinzhanMou]

@JohnnyB_222 Thanks! Yes, we support keyframe constraints during diffusion sampling (in-betweening, editing, expansion), and you can combine them with other test-time guidance, e.g. trajectory control.

[Linzhan Mou @LinzhanMou]

@DSqi4TZ4nm29308 @SIGGRAPHAsia Also have your agent read the walk-related training captions in https://t.co/6OszQOS3Eh and match that prompt style

[Linzhan Mou @LinzhanMou]

@DSqi4TZ4nm29308 @SIGGRAPHAsia Prompt tweaking alone is hard to control. Let your Codex refine the motion directly with Blender MCP: load the result into Blender and fix the bones and keyframes there.

[Linzhan Mou @LinzhanMou]

@rahul__gh0sh @frankzydou Code is MIT licensed, feel free to use it commercially!

[Linzhan Mou @LinzhanMou]

@victor_vibing Already out: https://t.co/92PHV0ZZqy

[Linzhan Mou @LinzhanMou]

@sebuzdugan Agreed, foot sliding is still an issue. We haven't designed a unified contact model for heterogeneous rigs (e.g. winged creatures or fish). A natural next step is adding a controller or IK post-processing to handle contacts.

[Linzhan Mou @LinzhanMou]

@nuvolore Thanks! No HF demo yet, but all training/inference code and checkpoints are released. We're also considering a Blender add-on.

[Linzhan Mou @LinzhanMou]

@GokulEpiphany Thanks! For automatic rigging, check out these amazing works: AniGen, Puppeteer, and UniRig! https://t.co/CrdN56Rr0C https://t.co/gLAPMxZ82c https://t.co/b5K9huomJR

[Jiahui Lei @JiahuiLei1998]

This was a really challenging task when we first started thinking about a unified generative motion prior for large-scale, diverse animation skeletons! It took Linzhan months to prepare the first version of the dataset, and a lot of effort to figure out how to model these irregular structures. Now the data and models are all available!