Greg Durrett
@gregdnlp.bsky.social
CS professor at NYU. Large language models and NLP. he/him
Congrats to Prasann and all the other awardees! Full list is here: cra.org/about/awards...
Taulbee Report 2024
Visit the post for more.
cra.org
January 3, 2025 at 2:39 PM
Congrats to Prasann and all the other awardees! Full list is here: cra.org/about/awards...
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!
January 3, 2025 at 2:39 PM
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!
He then advanced our understanding of online DPO methods: how can we combine the strengths of reward models and DPO? (also at COLM 2024)
January 3, 2025 at 2:39 PM
He then advanced our understanding of online DPO methods: how can we combine the strengths of reward models and DPO? (also at COLM 2024)
...established a critical weakness of RLHF with open reward models: spurious correlation with length (COLM 2024)
January 3, 2025 at 2:39 PM
...established a critical weakness of RLHF with open reward models: spurious correlation with length (COLM 2024)