phding @cornell_cs @cornell_tech undergrad @uoftengineering, and is elsewhere most of the time
Joined July 2014
- Tweets46
- Following162
- Followers130
- Likes2.3K
Zizhao Chen retweeted
🧵Here is why all math departments and AI labs should pay me and every geometric topologist on earth 💸 10 million 💵 dollars each.
This is a joint finding with @suchenzang and @tonysilveti. Ladies and gentlemen, I introduce you to 💪 KnotBench 💪 (arxiv:2605.09900) by Liu & Liu
Zizhao Chen retweeted
Today’s AI models can’t even tie their own shoes.
New research—led by @ch272h—tests AI models in a 3D environment, finding they perform well at untangling basic knots but cannot tie knots from simple loops or convert one knot to another. @Cornell_Bowers
news.cornell.edu/stories/202…
Zizhao Chen retweeted
Merriam-Webster’s human editors have chosen ‘slop’ as the 2025 Word of the Year.
🧩Natural language isn’t all you need.
We’re great at evaluating text-based reasoning (MATH, AIME…) but what about long-horizon visual reasoning?
Enter 𝗞𝗻𝗼𝘁𝗚𝘆𝗺: a minimalistic testbed for evaluating agents on spatial reasoning along a difficulty ladder
✨ Why it matters
KnotGym gives us a lightweight yet expressive testbed for multi-modal long-horizon reasoning and planning.
🔗 Website: lil-lab.github.io/knotgym
📄 Paper: arxiv.org/abs/2505.18028
Joint work with @yoavartzi
I'm presenting on Friday. Details below:
Fri, Dec 5, 2025
11:00 AM – 2:00 PM PST
Exhibit Hall C,D,E #4505
Pic: knots inside USS midway museum near SD convention center
Hi all, I will be at #NeurIPS2025 to present my work on stress-testing looooooong visual reasoning with KnotGym🥨
Let's talk, whether or not your VLM that can see 14 million possible futures like Doctor Strange
Zizhao Chen retweeted
🧵 New paper: "Simple Context Compression" - we show that mean-pooling beats the widely-used compression-tokens method for compressing contexts in LLMs, while being simpler and more efficient!
with @yoavartzi
(1/7)
Zizhao Chen retweeted
Pushed a big update to LM-class (v2025.2) -- this second version makes a much more mature resource
Many refinements of lecture slides + significant improvements to the assignments
Many thanks to @ch272h @HuaYilun and @shankarpad8 for their work on the assignments
Zizhao Chen retweeted
🚨Modeling Abstention via Selective Help-seeking
LLMs learn to use search tools to answer questions they would otherwise hallucinate on. But can this also teach them what they know vs not?
@momergul_ introduces MASH that trains LLMs for search and gets abstentions for free!
💡Key idea: Reward accuracy but penalize searches during training. Under the right optimization pressure, LLMs learn to invoke search when their parametric knowledge is lacking. At inference, we simply remove this search access and treat any search invocation as a proxy for abstention!
Zizhao Chen retweeted
ToddlerBot 2.0 is released🥳! Now Toddy can also do cartwheels🤸! We have added so many features since our first release in February; see github.com/hshi74/toddlerbot… for more details. Threads🧵(1/n)
Why scaling data annotators at high costs, when you can scale users for free?
The talk for our work on Retrospective Learning from Interactions, which will be in ACL (once I figure out how to squeeze it shorter)
Gist: autonomous post-training from conversational signals for LLM bootstrapping ... look ma, no annotations! 🙌📈🚀
youtube.com/watch?v=qW8S308e…
Zizhao Chen retweeted
Time to democratize humanoid robots!
Introducing ToddlerBot, a low-cost ($6K), open-source humanoid for robotics and AI research.
Watch two ToddlerBots seamlessly chain their loco-manipulation skills to collaborate in tidying up after a toy session.
toddlerbot.github.io/
Zizhao Chen retweeted
NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address the comment made during the invited talk this afternoon, as it is something that NeurIPS does not condone and it doesn't align with our code of conduct. We are addressing this issue with the speaker directly.
NeurIPS is dedicated to being a diverse and inclusive place where everyone is treated equally.
Zizhao Chen retweeted
Mitigating racial bias from LLMs is a lot easier than removing it from humans!
Can’t believe this happened at the best AI conference @NeurIPSConf
We have ethical reviews for authors, but missed it for invited speakers? 😡
I’ll be at #NeurIPS distributing mugs and collecting arguments for and against whether ai today is intelligent 🍻🧋
I’m not sure what conclusion I can draw from this poll.
Credit goes to everyone participated in this mini poll. Thank you - you made my day!