🎯 How can we empower scientific discovery in millions of nature photos? Introducing INQUIRE: A benchmark testing if AI vision-language models can help scientists find biodiversity patterns- from disease symptoms to rare behaviors- hidden in vast image collections. Thread👇🧵

Could multimodal vision language models (VLMs) help biodiversity researchers retrieve images for their studies? 🤔 MIT CSAIL, UCL, iNaturalist, The University of Edinburgh, & UMass Amherst researchers designed a performance test to find out. Each VLM’s task: Locate & reorganize the most

[1/x] can we scale small, open LMs to o1 level? Using classical probabilistic inference methods, YES! Joint MIT CSAIL / Red Hat AI Innovation Team work introduces a particle filtering approach to scaling inference w/o any training! check out …abilistic-inference-scaling.github.io

Excited to share our work on evaluating LLM reliability! Even top LLMs still make mistakes on basic tasks–but this was previously hidden by noisy benchmarks. To fix this, we carefully cleaned 15 popular benchmarks to create "platinum" versions that better measure reliability.

This is a fascinating demo for exploring how o1, Claude, DeepSeek, and other LLMs fail on basic tasks. See for yourself: platinum-bench.csail.mit.edu/inspect

We're excited to welcome Julia Chae and Shobhita Sundaram next week on Wednesday, March 5th for a presentation on "Personalized Representation from Personalized Generation" - be sure to check out this session! Thanks to Ahmad Mustafa Anis for organizing this community event ✨

Very excited to host Julia Chae and Shobhita Sundaram next week at Cohere For AI to present their research on "Personalized Representation from Personalized Generation". Register for the session for free (Link in the original tweet).

had a great time giving a talk about probabilistic inference scaling and the power of small models at the IBM Research ML Seminar Series - the best talks end with tons of questions, and it was great to see everyone so engaged : ) youtube.com/watch?v=--3rsQ…

Very excited to share *GSM8K-Platinum*, a revised version of the GSM8K test set! If you’re using GSM8K, I highly recommend you switch to GSM8K-Platinum! We built it as a drop-in replacement for the GSM8K test set. Check it out: huggingface.co/datasets/madry…

Adapt object detectors to new data *without labels* with Align and Distill (ALDI), our domain adaptation framework published last week in Transactions on Machine Learning Research (with a Featured Certification [Spotlight]! Certified papers at TMLR)

Presenting PRPG at ICLR 2026 on Saturday in Singapore! Would love to chat / catch up throughout the week to feel free to reach out :)

Excited to share our ICLR 2025 paper, I-Con, a unifying framework that ties together 23 methods across representation learning, from self-supervised learning to dimensionality reduction and clustering. Website: aka.ms/i-con A thread 🧵 1/n

Drop by our poster at Hall 3 + Hall 2B, #99 at 10 AM SGT! Unfortunately none of us could travel, but our amazing friends Jyo Pari Julia Chae Shobhita Sundaram & Mark Hamilton — will be presenting it 🙌 Feel free to reach out with any questions — I’ll be online & cheering them on 💖

The call for applications has just been released for #CV4Ecology2026!! This three-week intensive program trains ecologists and conservation practitioners to develop their own AI tools for their own data. When: Jan 12-30, 2026 Where: SCBI SMSC

Call for papers for the second CV for Ecology workshop at ICCV is live!!

🚨 Good news! The submission deadline for the CV4E workshop at #ICCV2025 has been extended from July 4 to July 7! #CV4E #ICCV

[1/7] Paired multimodal learning shows that training with text can help vision models learn better image representations. But can unpaired data do the same? Our new work shows that the answer is yes! w/ Shobhita Sundaram Chenyu (Monica) Wang, Stefanie Jegelka and Phillip Isola

Over the past year, my lab has been working on fleshing out theory/applications of the Platonic Representation Hypothesis. Today I want to share two new works on this topic: Eliciting higher alignment: arxiv.org/abs/2510.02425 Unpaired rep learning: arxiv.org/abs/2510.08492 1/9

Excited to be co-organizing CV4E Workshop @ ICCV for the second year at #ICCV2025 in Honolulu! We have an amazing suite of panelists (+ speakers) this year, don't miss it 👀