Yuyang Li

Third-year PhD student at @PKU1898 Institute for AI.
BEng from @Tsinghua_Uni Dept. of Automation.
Working on tactile robotics / dexterous manipulation.

[Yinghan Chen @yinghan__chen]

Introducing TacThru: Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation, accepted to IEEE Robotics and Automation Letters (RA-L)!

Check out our project page for more details, videos, code, and hardware! 👇
https://t.co/lrn9HywF4M

[Delta Intelligence @delta_intelli]

Introducing Δ₀ (Delta-0), our humanoid foundation model for whole-body loco-manipulation.

One generalist policy. 69 degrees of freedom. Everyday tasks at near-human speed—from making a bed to putting on a record.

Watch Δ₀ in action.

[Yuyang Li @aidenli_thu]

An exploration on how robots can design & use tools. So proud of @yinghan__chen, Xiyao, and all the work behind this!

Yinghan is the first student I’ve mentored during my PhD. After twists and turns, it’s incredibly rewarding to see a rough idea grow into a paper.

[Yinghan Chen @yinghan__chen]

Can a robot design a tool from scratch? Introducing HOT: Robot Tool Design from Scratch via Behavior-Aware Hierarchical Optimization.
Check out our project page for more details, videos, and code! 👇
https://t.co/1YLAThub0W

[Yuyang Li @aidenli_thu]

High-resolution, full-hand tactile sensing isn’t just nice to have—it’s essential for intelligent, adaptive manipulation. An unforgettable collaboration with @ZIHANGZHAO2, @TengyuLiuAI, and a fantastic team of colleagues!

[Zihang Zhao @ZIHANGZHAO2]

Our paper, published in Nature Machine Intelligence, presents a system with full-hand tactile sensing and sensory-motor feedback for adaptive, human-like grasping, advancing embodied agents in real-world operation.

Article: https://t.co/LwN7ZzyOfx
Demo: https://t.co/rhi0cztkdp

[Siyuan Huang @siyuanhuang95]

🤖🤖🤖 Following RoboVerse, we introduce another work focused on Robotic Tactile Simulation - Taccel Simulator. Taccel is a high-performance simulation platform for vision-based tactile sensors and robots.

🚀🚀🚀 Boosted by Nvidia Warp, we optimize Taccel with highly parallelized simulations and support 900fps simulation with 4k+ parallel training envs.

🤝🤝🤝 Taccel is designed with user-friendly APIs and is easy to use. We open-sourced all the code and documentation. Feel free to try!

Project: https://t.co/AT0G7MGzqX
Preprint: https://t.co/wSMUqBCwQB
Code: https://t.co/H5CxVjg5Ke

[Haoran Geng @HaoranGeng2]

In my past research experience, finding or developing an appropriate simulation environment, dataset, and benchmark has always been a challenge. Missing features, limited support, or unexpected bugs often occupied my days and nights. Moreover, current simulation platforms are relatively fragmented—making it challenging to replicate the success of the RT-X dataset in unifying community efforts.

Introducing RoboVerse, we provide a unified platform, dataset, and benchmark for scalable and generalizable robot learning. We hope to build a shared foundation to combine the community efforts. RoboVerse includes:

MetaSim: We carefully designed a configuration system and a universal interface to align current robotic simulators. With MetaSim, you can use any simulator with the same code—bringing together the community’s diverse efforts under one framework!

RoboVerse Dataset and Benchmark: We unify popular simulation environments and benchmarks into a single cohesive system and introduce the RoboVerse dataset—a large-scale, high-quality synthetic dataset. Additionally, we propose a standardized benchmark across both imitation learning and reinforcement learning.

A cool feature enabled by our unified framework: Hybrid Simulation! You can now integrate physics engines and renderers from different simulators—e.g., using MuJoCo precise physics with Isaac photorealistic rendering. This not only elevates simulation fidelity but also significantly enhances real-world transfer performance across complex robotic applications.

Hopefully, our team’s efforts could serve the robotic community to thrive vibrantly in the years to come.

RoboVerse is open-sourced🥳!!!
Project Page: https://t.co/IJR1iuEW1L
Documentation: https://t.co/7Ff4uhbJR0
Github Repo: https://t.co/iLRpjSNokQ
Paper: https://t.co/LUMJrd6i5I

[Simulately @simulately12492]

#SimulatelyWeekly brings you the latest updates on robotics and simulation. We’re also introducing Simulately Daily for the newest robotics papers. Check them out here: https://t.co/qCbfpBdOuu

[Simulately @simulately12492]

#SimulatelyWeekly:

We're in the era of robotics and simulation🚀! @nvidia has released IsaacSim 4.0 and IsaacLab, tailored for simulation and robot learning, plus the GROOT project for humanoids! 🤖 More below 🧵:

Check https://t.co/6X8djIb2sJ for more robotics information:

[AK @_akhaliq]

Ag2Manip

Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations

Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, modern methods

[Yuyang Li @aidenli_thu]

Nan's demos are always impressive 🔥🔥

[AK @_akhaliq]

Scaling Up Dynamic Human-Scene Interaction Modeling

Confronting the challenges of data scarcity and advanced motion synthesis in human-scene interaction modeling, we introduce the TRUMANS dataset alongside a novel HSI motion synthesis method. TRUMANS stands as the

[Siyuan Huang @siyuanhuang95]

🔥A wonderful New Year gift for all the robotics researchers!

Do you still feel puzzled about all the simulators and their various functions and settings? Check out Simulately🤖! It is a toolkit that includes all the information you need for diverse simulators.

Simulately was started by several of my students, including @HaoranGeng2 and @aidenli_thu, and was further joined by researchers worldwide.

Simulately is fully open-sourced. The journey has just begun, and welcome to join us!

[Simulately @simulately12492]

(3/3)
Simulately (https://t.co/i73EkUQbqw) is where minds converge to help researchers in robotics around the globe. But to make it better, we need YOU! Join us on this journey by contributing to: https://t.co/GlNWqtBtHc!

[Simulately @simulately12492]

(2/3)
✨ Discover:
- Comprehensive simulator intros and centralized tutorials
- Handy code snippets and toolkits
- Curated insights on datasets & related research
- Customized Simulately GPT for instant answers at https://t.co/FcBKZ9KQmT

[Simulately @simulately12492]

(1/3)
🚀Excited to announce Simulately🤖, a go-to toolkit for robotics researchers navigating diverse simulators!

💻 Github: https://t.co/GlNWqtBtHc
🔗 Website: https://t.co/i73EkUQbqw

Let’s level up our robotics research with Simulately!
#Robotics #Simulators #ResearchTool

[Siyuan Huang @siyuanhuang95]

Presenting our ICCV23 work: Full-body Articulated Human-object Interaction this morning. It studies full-body human object interactions with articulated objects, especially chairs.

Come to Room Nord #110 poster and say hi!

https://t.co/NDYlbAE57m

[Siyuan Huang @siyuanhuang95]

3D-VisTA will be presented this morning at Room “Foyer Sud” - 075, welcome to our poster!

[Chen Wang @chenwang_j]

How to chain multiple dexterous skills to tackle complex long-horizon manipulation tasks?

Imagine retrieving a LEGO block from a pile, rotating it in-hand, and inserting it at the desired location to build a structure.

Introducing our new work - Sequential Dexterity 🧵👇

[Yuyang Li @aidenli_thu]

?

[Yifan Jiang @YifanJiang17]

😢