Yuming Gu

PhD candidate in @USC｜Previous @tiktok_us ｜break dancer

[Yuming Gu @yuming_gu]

4/4 A USC × Columbia × Starpilot collaboration—accepted for an oral presentation at an #RSS2026 workshop! 🎉Thanks to Zinan Li, @yiyang_ling , @binghao_huang,@snikolaidis19,@YunzhuLiYZ, @daniel_t_seita and others.
Paper:https://t.co/7NZKvoGzsg
Website https://t.co/Rc4XY1xBor

[Yuming Gu @yuming_gu]

Can a robot “feel” without a tactile sensor? 🤖

Introducing FELT: a vision-to-touch framework that generates per-finger pressure signals directly from RGB.

Trained on paired visuo-tactile data, FELT can augment vision-only datasets—and deploy without tactile sensors. 🧵

[Yuming Gu @yuming_gu]

3/4 FELT points toward scaling touch alongside vision: adding tactile signals to existing robot datasets without equipping every platform with fragile, specialized sensors.

[Jitendra MALIK @JitendraMalikCV]

I want to offer some unsolicited advice to computer vision researchers jumping into robotics. Don't focus too much on VLMs, VLAs etc. That's fine, but the real action is at the sensorimotor level. Most of the open problems in robotics are in manipulation, which is about hand-object interaction, and contacts and forces are central. Proprioception and tactile sensing are as important as vision. Don't get seduced by cherry-picked demos. You can't do robotics without doing robotics.

[Yuming Gu @yuming_gu]

@tingtin36139994 说的对 婷婷

[Saining Xie @sainingxie]

you can’t build superintelligence without first building supersensing

[Yuming Gu @yuming_gu]

@tingtin36139994 kudos

[Binghao Huang @binghao_huang]

Tactile interaction in the wild can unlock fine-grained manipulation! 🌿🤖✋

We built a portable handheld tactile gripper that enables large-scale visuo-tactile data collection in real-world settings.

By pretraining on this data, we bridge vision and touch—allowing robots to:
✅ Perform robust in-hand reorientation
✅ Control contact and force with precision

🔗 Project page: https://t.co/zcJBEzd23i

(1/6)

[Yuming Gu @yuming_gu]

Our paper has been accepted by CVPR 2025! 🚀🚀

Inference code / data / model is available now in https://t.co/T6kpp2JET0

Feel free to check it out! 🏀🏸👍

[AK @_akhaliq]

DiffPortrait360 just dropped on Hugging Face

Consistent Portrait Diffusion for 360 View Synthesis

[Yuming Gu @yuming_gu]

@JiaweiYang118 🤡 we've been cooked so well.

[Yuming Gu @yuming_gu]

Thank you AK for posting, inference model will be ready in a week.

[AK @_akhaliq]

DiffPortrait360 just dropped on Hugging Face

Consistent Portrait Diffusion for 360 View Synthesis

[Yuming Gu @yuming_gu]

@ndennler Congrats Nathan!!

[Yuming Gu @yuming_gu]

@MaltePrinzler Nice work!

[Yuming Gu @yuming_gu]

congrats! @snikolaidis19

[USC Thomas Lord Department of Computer Science @CSatUSC]

Congratulations, @snikolaidis19, who has been awarded a prestigious @OkawaFoundation Research Grant for his groundbreaking research in human-robot interaction 👏

https://t.co/etzmHn34w7

@USCViterbi @USCAdvComputing @gauravsukhatme

[Yuming Gu @yuming_gu]

@zhijianliu_ @UCSanDiego @HDSIUCSD Big Congrats!

[Yuming Gu @yuming_gu]

@UUUUUsher No☹️

[Luma @LumaLabsAI]

Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here https://t.co/rBVWU50kTc #LumaDreamMachine

[#CVPR2026 @CVPR]

An interactive overview of #CVPR2024 is now available check it out!

Link: https://t.co/Px2ZkrPxzH