Everyone fears AI will replace us. After 3 studies, I fear something quieter: it takes the imaginative parts of our jobs and leaves the admin. Not mass unemployment , mass demoralization. When AI reshapes your work, will you still recognize yourself? @TEDxBerlin1 #TEDxBerlin

In the past two months, our small Webapp Coding team have been cooking hard to make Gemini great at WedDev, and we are thrilled to claim the 👑! Yes, we saw your enthusiasm — pelican riding a bike, game controller, please keep trying and sending your best WebDev prompts to our the way! We love them! Besides Webdev Arena, we also achieved #1 on Design Arena across categories: website gen, game gen, ui component gen etc! Website lovers, designers, we can’t wait to hear your feedback!

✨ Very overdue update: I'll be starting as an Assistant Professor in CS at University of Minnesota, Twin Cities, Fall 2026. I will be recruiting PhD students!! Please help me spread the word! [Thread] 1/n

📢 New Preprint! 📢 arxiv.org/abs/2510.07662 TL;DR: textual entailment and token probability behave very differently as bias evaluation metrics, even on the exact same bias definitions. Also, I'm looking for summer 2026 research internships in responsible AI - please reach out!

🎉 Excited to share our ACL 2025 paper: 🤖R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic Memory 🧠 📄 Paper: arxiv.org/abs/2501.12485 📍Poster: Hall 4/5, Session 4 Wednesday, July 30 11:00-12:30 🧵👇

Can you tell what actions are being mimed in this video? If so, you’re smarter than AI models! Check the last tweet in this thread for answers. In a new paper, we present MIME, which evaluates whether vision language models (VLMs) have a robust understanding of human actions. 🧵

How to enjoy the best of both worlds of efficient training (less communication and computation) and inference (constant KV-cache)? We introduce a new efficient architecture for long-context modeling – Megalodon that supports unlimited context length. In a controlled head-to-head comparison with Llama2, Megalodon achieves better efficiency and accuracy than Transformer in the scale of 7B and 2T training tokens.

AI/nsiders, ISI's podcast, is hosted by AI Division Director Adam Russell. In this week's episode, In this week's episode, @HJCH0 , a Research Assistant at ISI, explains why he’d consider himself a “global citizen.” Listen here: bit.ly/49ALjdy

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length abs: arxiv.org/abs/2404.08801 repo: github.com/XuezheMax/megalod…