Yoav Artzi

Yoav Artzi

@yoavartzi.com

LM/NLP/ML researcher ¯\_(ツ)_/¯ yoavartzi.com / associate professor @ Cornell CS + Cornell Tech campus @ NYC / nlp.cornell.edu / visiting researcher @ Google DeepMind / building @colmweb.org / previously associate faculty director @ arXiv.org

5.7K followers308 following549 posts

Yoav Artzi reposted

⚠️ Stop pretraining your looped Transformer with a separate KV cache per recursion! In our recent preprint, we show that *memory sharing* not only saves memory but is also a net-positive inductive bias! Less memory, same flops, higher quality. 🔗 arxiv.org/abs/2610.02383 🧵

Simple, straightforward, and just work well: looping with no KV overhead, and this also gives you a gradients highway that makes backprop work much better

Giovanni Monea@giomonea.bsky.social

⚠️ Stop pretraining your looped Transformer with a separate KV cache per recursion! In our recent preprint, we show that *memory sharing* not only saves memory but is also a net-positive inductive bias! Less memory, same flops, higher quality. 🔗 arxiv.org/abs/2610.02383 🧵

Yoav Artzi reposted

We released tickets to our waiting list (as of yesterday). If you were on the wait list, please check your email. Tickets that are not claimed will be re-distributed. The wait list remains open, so sign up if interested

Yoav Artzi reposted

We are delaying general registration to Aug 10 to carefully manage author registration and make sure that all authors (main + workshops) get to register. We appreciate the patience

Alt text

The COLM abstract deadline is approaching fast --> March 26! Full paper deadline is March 31 Verify using the COLM template (and font!) to avoid silly desk rejections. Careful of copy-pasting from other venue submissions, because it often overrides our template

Very excited about @nthngdy.bsky.social's new work! It really gets to the bottom (or top, depends where the head in LMs is 😜) and fundamentals of contemporary LLMs. A real treat of a paper: solid theory, and very cool experiments.

Nathan Godey@nthngdy.bsky.social

🧵New paper: "Lost in Backpropagation: The LM Head is a Gradient Bottleneck" The output layer of LLMs destroys 95-99% of your training signal during backpropagation, and this significantly slows down pretraining 👇

This call is still open. I am looking to recruit, as well as many other faculty at Cornell. We review folders as they come, and will send offers until all positions are filled. Please share with your network 🙏

Yoav Artzi@yoavartzi.com

Cornell is recruiting for multiple postdoctoral positions in AI as part of two programs: Empire AI Fellows and Foundational AI Fellows. Positions are available in NYC and Ithaca. Deadline for full consideration is Nov 20, 2025! academicjobsonline.org/ajo/jobs/30971

Yoav Artzi reposted

Submit to COLM! Deadline of March 31. This llama gets to enjoy his holidays and isn't stressed out just yet...

COLM 2026 is just around the corner! Mark your calendars for: 💡 Abstract deadline: Thursday, March 26, 2026 📄 Full paper submission deadline: Tuesday, March 31, 2026 Call for papers (website coming soon): docs.google.com/document/d/1...

Zoe presented this paper at NeurIPS D+B: it's all knots(🪢🪢🪢!?), no language tokens were harmed (or reinforced) in the process It's such a fun and creative paper, a real mind twist ;) You really get to think carefully about visual intelligence looking at these knots 🪢

Zizhao Chen@ch272h.bsky.social

🧩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

Yoav Artzi reposted

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

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.bsky.social, Yilun Hua, and Shankar Padmanabhan for their work on the assignments

I am potentially recruiting a postdoctoral fellow through this program. If interested, name me as a mentor, and ping me to let me know that you are applying! The process includes some sort of interview, so I can try to squeeze a few of these in advance (it will help a lot!)

Yoav Artzi@yoavartzi.com

Cornell is recruiting for multiple postdoctoral positions in AI as part of two programs: Empire AI Fellows and Foundational AI Fellows. Positions are available in NYC and Ithaca. Deadline for full consideration is Nov 20, 2025! academicjobsonline.org/ajo/jobs/30971

Yoav Artzi reposted

Congratulations to Alane Suhr '22, a #CornellTech Ph.D. #alumni advised by associate professor Yoav Artzi, for receiving the prestigious 2022 @aaai.org / @acmsigai.bsky.social Doctoral Dissertation Award! Read more about the award here: aaai.org/about-aaai/a... @yoavartzi.com

aaai.orgAAAI/ACM SIGAI Doctoral Dissertation Award - AAAIThe AAAI/ACM SIGAI Doctoral Dissertation Award recognizes and encourages superior research and writing by doctoral candidates in AI.