David Klindt

🧵 New paper! We explore sparse coding, superposition, and the Linear Representation Hypothesis (LRH) through identifiability theory, compressed sensing, and interpretability research. If neural representations intrigue you, read on! 🤓 arxiv.org/abs/2503.01824

Anyone knows adam?

Quick thread on the recent IMO results and the relationship between symbol manipulation, reasoning, and intelligence in machines and humans:

The AI field is now split into (A) a "traditional" ml/dl domain, and (B) a "psycho-AI" domain where innovation requires an understanding of / intuition about the cognitive capabilities of pretrained models and how to prompt / fine-tune them. These two fields are IMO separated.

Here's how my recent papers & reviews are going: * To solve a vision problem today, the sensible thing is to leverage a pre-trained VLM or video diffusion model. Such models implicitly represent a tremendous amount about the visual world that we can exploit. * Figure out how to…

🔥 Mark your calendars for the next session of the @ELLISforEurope x UniReps Speaker Series! 🗓️ When: 31th July – 16:00 CEST 📍 Where: ethz.zoom.us/j/66426188160 🎙️ Speakers: Keynote by @Pseudomanifold & Flash Talk by @FlorentinGuth 👉 Stay updated by joining our Google group:…

Are you studying how structure shapes computation in the brain and in AI systems? 🧠 Come share your work in San Diego at NeurReps 2025! There is one month left until the submission deadline on August 22: neurreps.org/call-for-papers

I wrote a fun little article about all the ways to dodge the need for real-world robot data. I think it has a cute title. sergeylevine.substack.com/p/sporks-of-agi

Ready to present your latest work? The Call for Papers for #UniReps2025 @NeurIPSConf is open! 👉Check the CFP: unireps.org/2025/call-for-… 🔗 Submit your Full Paper or Extended Abstract here: openreview.net/group?id=NeurI… Speakers and panelists: @d_j_sutherland @elmelis @KriegeskorteLab…

After studying the mathematics and computation of Sparsity for nearly 20 years, I have just realized that it is much more important than I ever realized before. It truly serves as *the* model problem to understand deep networks and even intelligence to a large extent, from a…

one thing I love about being in mech interp right now is how often I see fun papers at the intersection of interp & my special interests (in this case haematology). truly is so fun 🥺

Join us for the 3rd edition of the UniReps Workshop at #NeurIPS2025! 🧠🤖 We're bringing together researchers from #AI, #Neuroscience, and #CogSci to explore why different neural models learn similar representations. 📝 Call for Papers is OPEN on OpenReview! 🌐 Website:…

The call for papers for the NeurIPS Mechanistic Interpretability Workshop is open! Max 4 or 9 pages, due 22 Aug, NeurIPS submissions welcome We welcome any works that further our ability to use the internals of a model to better understand it Details: mechinterpworkshop com

I am heading to @icmlconf to present our position paper with @randall_balestr @klindt_david @wielandbr on what we believe are the important next steps to advance SSL. It's not either theory or practice, it's both. We as a community need a better discussion.

Join us in San Diego this NeurIPS for a workshop on Foundation Models for the Brain and Body - bringing together researchers building large-scale models for biosignals in academia and industry. It's an exciting time to decode the brain and body.

🚨 Registration is live! 🚨 The New England Mechanistic Interpretability (NEMI) Workshop is happening August 22nd 2025 at Northeastern University! A chance for the mech interp community to nerd out on how models really work 🧠🤖 🌐 Info: nemiconf.github.io/summer25/ 📝 Register:…