🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I'm putting together a quick reading list of papers related to o1 & test-time scaling for grad students following this area. github.com/srush/awesome-… Please send related papers, speculation. It's a fun topic to follow.

It's cool to see Google DeepMind's new research to show similar findings as we did back in April. IsoBench (isobench.github.io, accepted to Conference on Language Modeling 2024) was curated to show the performance gap across modalities and multimodal models' preference over text modality.

🧵When should LLMs trust external contexts in RAG? New paper from Yukun Huang and Sanxing Chen enhances LLMs’ *situated faithfulness* to external contexts -- even when they are wrong!👇

I will be presenting my work at #EMNLP2024 this Thursday on inference-time scaling and reasoning, come and chat! 🤔Motivation: We investigated multiple inference-time scaling methods/reasoning strategies and found that they are often not compared fairly. This can be misleading.

I am recruiting PhD students at Duke! Please apply to Duke CompSci or Duke CBB if you are interested in developing new methods and paradigms for NLP/LLMs in healthcare. For details, see here: monicaagrawal.com/home/research-…. Feel free to retweet!

Releasing METAGENE-1: In collaboration with researchers from USC, we're open-sourcing a state-of-the-art 7B parameter Metagenomic Foundation Model. Enabling planetary-scale pathogen detection and reducing the risk of pandemics in the age of exponential biology.

Excited that we get to present this at #NAACL2025 main conference! TL;DR: We introduced MatViX, a benchmark for multimodal (text + images, including charts, plots, and tables) information extraction from full-length scientific documents.

I'll be visiting the Flatiron Institute until Jan 26. Friends in NYC, feel free to reach out!

To appear at ICLR 2025, "Training Neural Networks as Recognizers of Formal Languages", and new benchmark, 🔥FLaRe🔥, for Formal Language Recognition! With Ghazal Khalighinejad, Anej Svete, Josef Valvoda, Ryan Cotterell, and Brian DuSell. See thread below.

I won’t be at #ICLR2025, but our poster (#362) will be up in Hall 3 + Hall 2B on Thu, Apr 24 at 10 AM. DMs are open if you’d like to chat — or come find me at #NAACL next week! :)

I’m giving an oral talk on MatViX at #NAACL2025 on Thursday, May 1st at 16:30. Come by if you’re around!

Excited to share that I'll be joining Google Sunnyvale this summer as a Student Researcher, where I'll be working on model embeddings and retrieval. Would love to meet up with old and new friends in the Bay :)