Trinity Chung

@gs_ai_ working on the best simulator for robotics! previously @CMU_Robotics @BerkeleyCDSS

[Trinity Chung @Milotrince]

1/ Progress in robot locomotion scaled with simulation, but touch was left behind. Our work, Tactile Genesis, unlocks sim for dexterous manipulation. Using sim to ablate tactile types and models, we can quickly converge to better tactile hardware and force-informed policies.

[Trinity Chung @Milotrince]

The latest Genesis World v1.3.0 releases differentiable sim, better friction, and update for tactile sensors. Check it out! https://t.co/rKSgvr4mAr

[Trinity Chung @Milotrince]

and a brave decision! we all have to operate within the limits of our own biology🥲

[Lilian Weng @lilianweng]

It is a hard and sad decision. I shared this message with folks at Thinky. Thank you all for the time together♥️ Just as the last sentence in my message: The future worth building is human.

[Trinity Chung @Milotrince]

@KunTao221218 Yes, our experiments show including full force torque tactile information allows student policies to reach the oracle policy.

[Trinity Chung @Milotrince]

1/ Progress in robot locomotion scaled with simulation, but touch was left behind. Our work, Tactile Genesis, unlocks sim for dexterous manipulation. Using sim to ablate tactile types and models, we can quickly converge to better tactile hardware and force-informed policies.

[Trinity Chung @Milotrince]

@jayjunleee Yes I referenced your work heavily, thank you!!

[Trinity Chung @Milotrince]

Calibrating sim with real tactile sensors is still hard. We don't know yet if some other representations may be the answer!

[Akash Sharma @akashshrm02]

Presenting PTLD: an approach to learning tactile dexterous policies without ever simulating the tactile sensor.

Tactile is essential for performing highly dexterous manipulation. However, collecting tactile observations reliably has been a fundamental bottleneck: (1) teleoperating a multi fingered hand for dynamic tasks is challenging, making sim-to-real imperative, (2) one can’t realistically simulate tactile today

[Max Simchowitz @max_simchowitz]

Robotics people, follow @aran_nayebi . He's been asking some really fundamental questions about what morphologies we need for robotics, and comes from a really unique bio/neuro perspective. Check this work out!

[Trinity Chung @Milotrince]

@cspaliwa1 I have limited experience with real tactile hardware, I only know what I've read and heard. I'll leave the exploration up to the community. Upcoming conferences will have tons of tactile papers.

[Trinity Chung @Milotrince]

@Em_Nomadic Yes! This is the true value of good simulation :) not just as a worse/cheap fallback for reality, which is the way policy training people see sim as..

[Trinity Chung @Milotrince]

@_varunnair @nvidia It's funny because IsaacSim actually does have a tactile sensor, but it was integrated quietly. Mimics GelSight, works on flat pad only https://t.co/F9y2yzuyrq

[Trinity Chung @Milotrince]

9/ Thanks to my advisors @aran_nayebi @KaterinaFragiad and collaborators @kashu_yamazaki @gs_ai_ for supporting me throughout this work! ❤️ Follow them for more cutting edge NeuroAI and robotics research🧠🦾

[Trinity Chung @Milotrince]

8/ For a more complete discussion on my work in tactile sensing, my master's thesis presentation is available at https://t.co/CqVcO4FBrI 😄

[Aran Nayebi @aran_nayebi]

🚀 New Open-Source Release! PyTorchTNN 🚀

A PyTorch package for building biologically-plausible temporal neural networks (TNNs)—unrolling neural network computation layer-by-layer through time, inspired by cortical processing. PyTorchTNN naturally integrates into the Encoder-Attender-Decoder (EAD) architecture (Chung*, Shen* et al., 2025), which flexibly combines diverse neural networks, motivated by the fact that no single model (Transformer, SSM, RNN) dominates all sequence learning tasks.
🧵👇

[Haoran Geng @HaoranGeng2]

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate?

🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch.

🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks.

Code is fully released; check out our:
Homepage: https://t.co/I8kVJO3XPw
Paper link: https://t.co/BFqpOwXYbT
Github: https://t.co/345eTpTx0y