🔥Telegram İfşa

Soon en route for #chi2025! Will be presenting this work Wednesday 4/30 in Technology-Facilitated Family Interaction session :3!! See you in Japan 😊🌸

Hi friends, I will be at #NAACL2025 to present: 🧷 AI-LieDar: a framework to study LLMs navigating truthfulness-utility conflicts in interactions, and we found agents "lie" in goal-driven tasks with truthfulness rates below 50% 🫨 🧷 Sotopia-S4: a demo for our Sotopia

My PhD advisor and mentor at MIT Media Lab, Professor Pattie Maes, receives the Lifetime Research Award for pioneering human-agent interaction! Congratulations Pattie! 👏👏👏 Fluid Interfaces Pattie Maes @aha_medialab @mitmedialab

When you and your best friend both win paper awards at #chi2025 for your internship work 🥹🫶. Apple do we get free candy apples for rest of trip 👀🍎

Language model (LM) agents are all the rage now—but they may have cognitive biases when inferring causal relationships! We eval LMs on psych task to find: - LMs struggle with certain simple causal relationships - They show biases similar to human adults (but not children) 🧵⬇️

Hand gestures are a major mode of human communication, but they don't always translate well across cultures. New research from Akhila Yerukola, Maarten Sap (he/him) and others is aimed at giving AI systems a hand with overcoming cultural biases: lti.cmu.edu/news-and-event…

Thanks Language Technologies Institute | @CarnegieMellon and CMU School of Computer Science for featuring our work!!✨💫 Our paper on culturally offensive nonverbal gestures is accepted to #ACL2025 main! Detailed thread🧵: x.com/akhila_yerukol… Preprint📜: arxiv.org/abs/2502.17710 Work done with Saadia Gabriel Violet Peng Maarten Sap (he/him)

📢 today's scaling laws often don't work for predicting downstream task performance. For some pretraining setups, smooth and predictable scaling is the exception, not the rule. a quick read about scaling law fails: 📜arxiv.org/abs/2507.00885 🧵1/5👇

TLDR: Mirai is an app that helps you build confidence and resilience by letting you talk to your “ideal self” -- in a voice that sounds like you. Our MIT research shows that this simple, self-referencing interaction can rewire how you think about yourself. === Ever notice how

This work has been accepted to #COLM2025 . If you are in Montreal this week for Conference on Language Modeling and would like to chat about this (or anything related to discovery / exploration / RL), drop me a note! Poster session 2: Tuesday Oct 7, 4:30-6:30pm Poster number 68

Congratulations to our own Maarten Sap on the tremendous honor of being named a 2025 Packard Fellow!