iiinova — where your digital self keeps evolving

Greg Durrett

@gregdnlp.bsky.social

2.6K followers 413 following 28 posts

CS professor at NYU. Large language models and NLP. he/him

Posts Replies Media

Greg Durrett @gregdnlp.bsky.social · 25/03/2026

ICML reviews have you considering this? Please look at our final submission instructions for COLM below!

Image of a llama driving a car taking an exit towards COLM instead of continuing to ICML.

071

Greg Durrett @gregdnlp.bsky.social · 02/12/2025

📢 Postdoc position 📢 I’m recruiting a postdoc for my lab at NYU! Topics include LM reasoning, creativity, limitations of scaling, AI for science, & more! Apply by Feb 1. (Different from NYU Faculty Fellows, which are also great but less connected to my lab.) Link in 🧵

22112

Greg Durrett @gregdnlp.bsky.social · 07/10/2025

Find my students and collaborators at COLM this week! Tuesday morning: @juand-r.bsky.social and @ramyanamuduri.bsky.social 's papers (find them if you missed it!) Wednesday pm: @manyawadhwa.bsky.social 's EvalAgent Thursday am: @anirudhkhatry.bsky.social 's CRUST-Bench oral spotlight + poster

095

Greg Durrett @gregdnlp.bsky.social · 03/01/2025

Before his post-training work, Prasann did a great project on representing LM outputs with lattices, which remains one of my favorite algorithms-oriented papers from my group in the last few years, with a lot of potential for interesting follow-up work!

130

Greg Durrett @gregdnlp.bsky.social · 03/01/2025

He then advanced our understanding of online DPO methods: how can we combine the strengths of reward models and DPO? (also at COLM 2024)

120

Greg Durrett @gregdnlp.bsky.social · 03/01/2025

...established a critical weakness of RLHF with open reward models: spurious correlation with length (COLM 2024)

110

Greg Durrett @gregdnlp.bsky.social · 03/01/2025

Huge congrats to @prasannsinghal.bsky.social for being one of the 8 CRA Outstanding Undergraduate Researcher Award winners! It has been an absolute privilege to work with Prasann during his time at UT. (And he's applying for PhD programs this year...hint hint...) Prasann's work 🧵

1224

Greg Durrett @gregdnlp.bsky.social · 08/12/2024

I'll be at #NeurIPS2024 w/ - @fcyin.bsky.social's LoFiT: using interp to improve fine-tuning (Weds pm poster & MINT spotlight talk Sun) - @thomlake.bsky.social's analysis of Overton pluralism (Pluralistic alignment Sat) Please reach out to me to chat about interp, factuality, reasoning, &c!

1468

Greg Durrett @gregdnlp.bsky.social · 22/11/2024

when a famous person just got here and you temporarily have more followers than they do

"I'm the captain now" meme with top text "Look at me" and bottom text "I'm the influencer now"

41093

Greg Durrett @gregdnlp.bsky.social · 13/11/2024

I won't be at EMNLP, but come and see: 🔍 Detecting factual errors from LLMs (Liyan Tang) 🛠️ Detect, critique, & refine pipeline (Manya Wadhwa and Lucy Zhao) 🏭 Synthetic data generation (Abhishek Divekar) 📄 Fact-checking (Aniruddh Sriram) at FEVER t.co/fQbl0G7m23 (1st real post in the bluer skies!)

Image of the linked website listing EMNLP paper titles, authors, and locations

1204