Personal vision tasks–like detecting *your mug*-are hard; they’re data scarce and fine-grained. In our new paper, we show you can adapt general-purpose vision models to these tasks from just three photos! 📝: arxiv.org/abs/2412.16156 💻: github.com/ssundaram21/perso… (1/n)

new preprint: language models are “insecure” reporters. researchers and engineers have become increasingly reliant on LLM-written reports---second-hand accounts of code and experiments---to understand agent-generated work. in this study, we ask: “how transparent are these LLM-generated reports?” 🔍

Taking a short break from LLM research to go back to my roots. Introducing... Concept Lenses! A training-free way to do similarity search along whatever concept you care about. Typically, embedding-based similarity search is constrained by whatever notion of similarity the model learned in training. This means that if the model is primed for semantic similarity, but you actually care more about visual appearance, you'd need to switch models. Under a Concept Lens projection, though, distance between embeddings means distance only along the concept you care about. Blog post: jasperlu.com/blog/prompted-s… Demo: jasperlu.com/projects/concep…

X-rays are everywhere in medicine, but extracting general, quantitative anatomical information from them remains remarkably difficult. Announcing FleXray: an open-source, open-weight model for zero-shot anatomical segmentation across the human body—from different regions, viewing angles, and acquisition settings. FleXray learns from large-scale synthetic supervision generated from 3D anatomy, then transfers directly to real clinical X-rays. Try it now on your own X-rays in our in-browser demo! 🧵 1/N — project page, demo, weights, code & paper below ↓

For AI to work with us, it needs to understand us Today, we're introducing Persimmon, the first large-scale model designed to realistically simulate how people talk and interact

iNaturalist has 300M+ images with ecological signals—diet, habitat, etc.—visible but rarely annotated and thus inaccessible at scale. Can AI help scientists access these signals from raw imagery? INQUIRE-Search makes large ecological databases discoverable via natural language.

Our Archival Track deadline is coming up soon and has been extended to July 15th! Looking forward to another great round of submissions 🙂

I'll be at #ICML2026 to present our *spotlight* work! TLDR: LLMs can learn to self-generate curricula for problems they can't yet solve, using self-play with meta-RL. Please reach out to chat about self-improving agents, synthetic data & environments, curriculum learning, or anything else! We've updated the paper with some fun additions ⬇️

Excited to share ID-Sim, our identity-focused similarity metric, presenting at #CVPR2026 this week in Denver! 🎉 Humans are remarkably good at distinguishing highly similar objects across different contexts. We asked: can we train a metric that does the same?

Excited to share ID-Sim, our identity-focused similarity metric, presenting at #CVPR2026 this week in Denver! 🎉 Humans are remarkably good at distinguishing highly similar objects across different contexts. We asked: can we train a metric that does the same?

Excited to share ID-Sim, our identity-focused similarity metric, presenting at #CVPR2026 this week in Denver! 🎉 Humans are remarkably good at distinguishing highly similar objects across different contexts. We asked: can we train a metric that does the same?

Excited to share ID-Sim, our identity-focused similarity metric, presenting at #CVPR2026 this week in Denver! 🎉 Humans are remarkably good at distinguishing highly similar objects across different contexts. We asked: can we train a metric that does the same?