Dirk Hovy

dirkhovy.bsky.social

03 May 2025 14:17

We (w/ @diyiyang.bsky.social, @zhuhao.me, & Bodhisattwa Prasad Majumder) are excited to present our #NAACL25 tutorial on Social Intelligence in the Age of LLMs! It will highlight long-standing and emerging challenges of AI interacting w humans, society & the world. ⏰ May 3, 2:00pm-5:30pm Room Pecos

Elizabeth Mieczkowski

emiecz.bsky.social

27 March 2025 18:56

We often assume that specialized roles improve performance in multi-agent systems, but when does specialization emerge based on a given task and environment? 🧵👇 ⭐️ New preprint w/ Ruaridh Mon-Williams, @neilbramley.bsky.social, Chris Lucas, @natvelali.bsky.social & @cocoscilab.bsky.social

Martin Wattenberg

wattenberg.bsky.social

22 March 2025 08:11

Neat visualization that came up in the ARBOR project: this shows DeepSeek "thinking" about a question, and color is the probability that, if it exited thinking, it would give the right answer. (Here yellow means correct.)

Jennifer Hu

jennhu.bsky.social

14 March 2025 01:20

Check out our new work on introspection in LLMs! 🔍 TL;DR we find no evidence that LLMs have privileged access to their own knowledge. Beyond the study of LLM introspection, our findings inform an ongoing debate in linguistics research: prompting (eg grammaticality judgments) =/= prob measurement!

Jia-Bin Huang

jbhuang0604.bsky.social

12 March 2025 04:57

How a 40-Year-Old Trick Solves Seamless Image Blending Laplacian pyramid blending is a simple yet effective tool for many applications, including object composition, seamless panorama stitching, and exposure fusion. Let’s learn this classic method that still works so well today.