Siqiao Huang

Rising senior undergrad, Yao class @Tsinghua_Uni | Current intern @uwcse | World Models, WAMs, Humanoid Foundation Models | RS @wuji_global | Prev. RA @mldcmu.

[Siqiao Huang @KnightNemo_]

In the last couple of months, we have witnessed significant advances in Industry-scale World Models. Yet, for the broader community, the gap between reading about these models and deploying them remains disappointingly wide.

Today we're releasing Nano World Models: a minimalist, batteries-included repo for advancing world model science.
🧵 (1/9)

[Siqiao Huang @KnightNemo_]

@guanqi_he Congrats!!

[Siqiao Huang @KnightNemo_]

If you are interested in Locomotion, definately chat with @RunhanH !!

[Runhan Huang @RunhanH]

Flexible Locomotion Learning with Diffusion Model Predictive Control

Excited to share that our paper has been accepted to #ICRA2026 @ieee_ras_icra!

A diffusion-planning framework for flexible real-world quadruped locomotion. Instead of learning a fixed RL policy or relying on hand-crafted dynamics for MPC, we train a diffusion trajectory prior that jointly predicts future states and actions.

Key Ideas:

Diffusion-MPC: A diffusion planner unlocks flexible locomotion through test-time reward and constraint adaptation
Interactive reward-weighted finetuning enables continual behavior refinement from online environment feedback
Real-world deployment on Unitree Go2 with efficient and adaptive planning

The same planner can adapt at test time to height changes, posture/joint constraints, balancing under external disturbances, energy-aware locomotion, and zero-shot outdoor walking on grass and slopes.

🌐Homepage: https://t.co/TSXUZAL5nT
📖Paper: https://t.co/de4dUZf5AA
🔗Code: https://t.co/NLFB1alhWJ

This work is by @RunhanH, Haldun Balim, @hankyang94 , and @du_yilun.

#ICRA2026 #Robotics #LeggedRobots #RobotLearning #DiffusionModels #MPC #MachineLearning

[Siqiao Huang @KnightNemo_]

@perryadong Goat!

[Siqiao Huang @KnightNemo_]

@Kevin_GuoweiXu Congrats on the new work! So productive.

[Siqiao Huang @KnightNemo_]

We need a sglang/vllm but for world model serving. The year that this need becomes apparent and the project that will do it becomes well-known is 2028.

[Siqiao Huang @KnightNemo_]

@vai_viswanathan Thank you for trying it out!

[Siqiao Huang @KnightNemo_]

@ShenyuanGao Thanks, Shenyuan!!!

[Siqiao Huang @KnightNemo_]

In the last couple of months, we have witnessed significant advances in Industry-scale World Models. Yet, for the broader community, the gap between reading about these models and deploying them remains disappointingly wide.

Today we're releasing Nano World Models: a minimalist, batteries-included repo for advancing world model science.
🧵 (1/9)

[Siqiao Huang @KnightNemo_]

@paolodiprodi Thank you for your interest! We will add a contributing guideline recently.

[Max Simchowitz @max_simchowitz]

Congratulations to Siqiao ( @KnightNemo_ ) for releasing his NanoWorldModels repo.

World model research can be notoriously tricky, given the numerous small design decisions that can make an excellent idea appear to fail completely. Siqiao's repo will help all researchers avoid these pitfalls; a huge service to the community!

[Siqiao Huang @KnightNemo_]

Nano World Models is a team effort, and I’m deeply grateful to everyone who helped make it possible. Special thanks to @max_simchowitz for guidance and mentorship along the way, and to the whole team ( @k4sncdrnng, @mqchenner, @HengkaiPan, @lomarchehab, @fermorenp) for everything behind this work!

[Siqiao Huang @KnightNemo_]

World Models need the World. Our hope is to build a Babel tower for world model research: datasets, objectives, architectures, and tasks all speaking the same language. We invite the global community to join us, contribute, and build this future together. Learn more:
📚 Paper: https://t.co/9or1ydHoOp
📝 Blog: https://t.co/oMEK5JFT84
🤖Models: https://t.co/t3FArxxTqv
💻 Code: https://t.co/STOAC1vzgL

🧵 (9/9)