On prompt, where the small model can get non-trivial success rates, basically spending X FLOPs on test-time compute > spending those X on pre-training compute w/ both verifiers & revisions. On prompts where the small model is totally bad, we need to spend pre-training compute.

🪃 I'm on the academic job market! I study digital applications for work, focusing on mental well-being + social dynamics. My work merges AI, sensing, informatics, and organizational science to help workers work differently. Pls bump and keep an eye out: vedantswain.com

🎉The coolest #CSE school in the world is hiring multiple faculty members! Application link below👇

☀️Excited to share our new paper! Generative AI agents are powerful but complex—how do we design them for transparency and human control? 🤖✨ At the heart of this challenge is establishing common ground, a concept from human communication. Our new paper identifies 12 key

Check out our new work, led by Mohit Chandra! In addition to evaluating the classification-style diagnostic capabilities of LLMs for psychiatric ADRs, we conduct a multi-dimensional evaluation to determine how closely LLM-generated responses align with expert responses. More below:

Pretty impressed by NVIDIA's Cosmos! As someone who's not in robotics research, I wondered how one goes from A→B, where: (A): generating video simulations of a world that I want to run a robot in (from a seed image and/or text instruction) and (B): getting the robot to actuate a

I've created slides for those curious about the recent rapid progress in linear attention: from linear attention to Lightning-Attention, Mamba2, DeltaNet, and TTT/Titans. Check it out here: sustcsonglin.github.io/assets/pdf/tal…

Excited to share that our work got accepted at #NAACL2025 Main. 🥳 1️⃣ How good are LLMs in detecting adverse drug reactions and providing mitigation strategies? 2️⃣ How can we measure LLM-expert alignment in long-form generations? To know more: shorturl.at/bldCb

Another week, another conference! CSE students and faculty are in Albuquerque presenting #NLProc research at NAACL! The GT @ #NAACL website is your one-stop shop for everything you need to know about our teams and their research! 🔗 sites.gatech.edu/research/naacl…

New paper from my group at Microsoft Research! 📄arxiv.org/abs/2507.07935 Promises about how AI will change work are cheap. What does the actual data say? We measured which work activities people use AI for, how successful they are, and which jobs do those tasks. 🧵1/8

🚀 I'm joining New York University as an Assistant Prof. + looking for PhD students in Human-Centered Technology, Innovation & Design! engineering.nyu.edu/news/nyu-tando… #AcademicTwitter [1/4]