great analysis on common reviewers mistakes/patterns and how to deal with them as an AC

What does a 1911 electroscope have to do with testing on your training data? Find out at my (remote) invited talk tomorrow @ CONDA #ACL2024 conda-workshop.github.io

The main conference has ended, but the ACL 2025 is not over. Tomorrow, Friday the 16th, come to the CONDA Workshop (Lotus Suite 4) for amazing talks by Anna Rogers, Jesse Dodge, @dieuwke, and MMitchell. Schedule: conda-workshop.github.io

The Data Contamination Workshop is tomorrow at #ACL2024NLP ! Come listen to MMitchell Dieuwke Hupkes Jesse Dodge Anna Rogers and a collection of amazing data contamination papers at Lotus Suite 4! Program: conda-workshop.github.io

The ATTRIB workshop is back @ NeurIPS 2024! We welcome papers connecting model behavior to data, algorithms, parameters, scale, or anything else. Submit by Sep 18! More info: attrib-workshop.cc Co-organizers: Tolga Bolukbasi Logan Engstrom Sadhika Malladi Elisa Nguyen Sam Park

Excited to share our paper about Imagen 3, Google's latest and most capable text-to-image model! arxiv.org/abs/2408.07009 It's been a big team effort. You can try it out on ImageFX, our experimental AI tech surface, now: aitestkitchen.withgoogle.com/tools/image-fx

lol

Intervention-based approaches to mechanistic interpretability have progressed at an astounding rate recently. In our new paper (a major update to a 2023 ms), we provide a formal framework and show how to express many methods within this framework: arxiv.org/abs/2301.04709

LAION, with all its problems, was an awesome resource and artifact. It's great to see its new version out!

Releasing OLMoE - the first good Mixture-of-Experts LLM that's 100% open-source - 1B active, 7B total params for 5T tokens - Best small LLM & matches more costly ones like Gemma, Llama - Open Model/Data/Code/Logs + lots of analysis & experiments 📜arxiv.org/abs/2409.02060 🧵1/9

I had lots of fun visiting Antoine Bosselut and his wonderful group last year. Would recommend applying! (And take some melatonin with you if you're doing a 3-day cross-atlantic trip like me 😂)

The yearly reminder of the "open workshop" where we started documenting and open-sourcing our material from the Big Picture workshop. Check it out if you're organizing a workshop this year bigpictureworkshop.com/open-workshop

Really excited about this new workshop we’re proposing for *CL! Memorization of training data is both fascinating to analyze and has a wide range of legal/privacy/benchmarking/social implications. Please vote if you’re interested!

When COT keywords appear mainly next to math and symbolic reasoning in the pretraining data, it makes COT work mainly with math and symbolic reasoning. x.com/yanaiela/statu…

Yanai Elazar pre-training data is the real moat 😎