a collection of set theorists who are so excited that they cannot contain themselves

LinkedIn is using your data to train generative AI. If you don't want that you need to opt out manually Opt-out link: linkedin.com/mypreferences/…

Thank you, Sameer Singh and Kat (@ CapitalOne NYC ), for inviting and hosting me at UCI yesterday! I loved meeting everyone and giving a talk on 🌎 AppWorld (appworld.dev)!

Alignment is necessary for LLMs, but do we need to train aligned versions for all model sizes in every model family? 🧐 We introduce 🚀Nudging, a training-free approach that aligns any base model by injecting a few nudging tokens at inference time. 🌐fywalter.github.io/nudging/

Interested in how many images of a concept are needed for text-to-image models to imitate them, or privacy and copyright implications of text-to-image models? Check out our work led by Sahil Verma ⬇️

📣 Curious about how language models handle linguistic uncertainty—and how they stack up against human interpretation? Our EMNLP 2024 paper dives deep! 🌊 Check it out: arxiv.org/pdf/2407.15814 and meet us in Miami next week! 😄 #EMNLP2024 🧵[0/9]

Poster at 10:30am on Wednesday!

Had a great time at #EMNLP2024! Met lots of old friends and new. Having the entire #UCINLP group around made it one of the most fun conferences I have attended!

One nice thing I learned from this episode is that nothing will happen to you if you ignore Underline's requests to upload slides, posters and recordings of your talk a month in advance, and in the future I encourage you to spend your time on more productive pursuits!

Still at the poster session? Come join us for keynote 3 by Sameer Singh!

Come listen to the hot takes of our panelist in the Brickell room! Do we still need generalisation evaluation? 🧐 #GenBench2024 #EMNLP2024

Had a fun week at #EMNLP2024 in Miami, meeting folks old and new, along with the #UCINLP lab retreat! See everyone at the next one! (PS, mostly on b_sky going forward)

Happy New Year! 🎉 2025 will be the only square year (45²) in many of our lifetimes.

:-)

🚀 Before DeepSeek AI Took Over the Hype Cycle, These Companies Were Already Building the Future Spiffy AI & Flipkart were scaling GenAI at massive levels—while most enterprises are still trying to figure it out. 🔥 In this must-listen Enterprise GTM Podcast: 🔹 Sameer Singh

Defended 🎉🎓 Big thanks to Roy Fox (@[email protected]), Sameer Singh, and labmates for their mentorship and support over the past 5 years!

Excited to present our work at #ACL2025NLP's Panel 2: LLM Alignment! 🚀 One of just 25 papers selected for panel out of 8300+ submissions—don't miss it! 🌐 Project: fywalter.github.io/nudging/ 🆕 Code (API & caching): github.com/fywalter/nudgi… 🆕 Interactive Demo: