C Zhang (@chongzitazhang) 's Twitter Profile
C Zhang

@chongzitazhang

Robotics @ETH_en.

Prev: @CMU_Robotics @Tsinghua_Uni.
.................
⚠️ Shitpost here.
📑 Read papers @RoboReading.
❌ Against killer robots.

ID: 1602376047093219329

linkhttp://zita-ch.github.io calendar_today12-12-2022 18:53:49

2,2K Tweet

4,4K Takipçi

523 Takip Edilen

Michael Posa (@michaelaposa) 's Twitter Profile Photo

Model-based control promises generalization--just add a model! Yet it's never been that easy. This summer, we wanted to show that we our C3+ controller COULD "Push Anything," just from a visual scan of an object. 33 different objects, including 4 simultaneously, 98% success rate

dar (@radbackwards) 's Twitter Profile Photo

I joined 1X because Bernt & Eric asked me if I could help them make NEO into something simple enough for anyone on earth to use and give it to the world. It felt like having a couple strangers come up to me and offer me a chance to change the world (well it was). I've never

Seohong Park (@seohong_park) 's Twitter Profile Photo

We scaled up an "alternative" paradigm in RL: *divide and conquer*. Compared to Q-learning (TD learning), divide and conquer can naturally scale to much longer horizons. Blog post: seohong.me/blog/rl-withou… Paper: arxiv.org/abs/2510.22512 ↓

We scaled up an "alternative" paradigm in RL: *divide and conquer*.

Compared to Q-learning (TD learning), divide and conquer can naturally scale to much longer horizons.

Blog post: seohong.me/blog/rl-withou…
Paper: arxiv.org/abs/2510.22512

↓
C Zhang (@chongzitazhang) 's Twitter Profile Photo

Cursed. Read some biokinetics paper claiming that vertical force after landing a jump is 100x body weight. Looking at the unit, it turns out to be 100x body mass (10g). Asked ChatGPT and Gemini if this could be true. Both models: yes coz force happens with a small delta t.

Ted Xiao (@xiao_ted) 's Twitter Profile Photo

Most of the 1X hate/hype misses what’s actually happening. This is not a product release! This is an audacious gambit. The AI is unsolved (by anyone), but 1X has started the shotclock. They are betting that autonomy timelines are short / can be shortened by Neo adopters.

Most of the 1X hate/hype misses what’s actually happening.

This is not a product release! This is an audacious gambit.

The AI is unsolved (by anyone), but 1X has started the shotclock. They are betting that autonomy timelines are short / can be shortened by Neo adopters.
Wenli Xiao (@_wenlixiao) 's Twitter Profile Photo

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD

C Zhang (@chongzitazhang) 's Twitter Profile Photo

Well... Torque accuracy by actuation or feedback? What does 95% mean for backdrivability? What is nominal load? Repetition and accuracy (does that mean precision?) of what? AI based adaptation means adaptive control with randomization of offsets instead of hardstop calibration?