🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Aran Nayebi Jeffrey Bowers Rylan Schaeffer Hi Aran Nayebi, just wanted to clarify that the paper Jeffrey Bowers has linked does use neural data. The paper posted by Meenakshi Khosla is a separate work. In the linked work we do highlight that model rankings change depending on the metric. (1/4) x.com/Ansh_soni1234/…

⁉️What do model-neural similarity scores tell us? To systematically explore this for different metrics, we develop new numerical tools & analytics to characterize what drives similarity scores and what constitutes a "good" score. (1/10)

Very happy to share a new paper that will appear in UniReps proceedings (unireps.org/2024). I show how two popular neural network comparison methods - CKA and RSA - can sometimes be equivalent, i.e. produce the exact same value. links below 👇

Excited to share that I'll be joining University of California at Irvine as a CS faculty in '25!🌟 Faculty apps: Krishna Murthy, Zhuang Liu & I share our tips: unnat.github.io/notes/Hidden_C… PhD apps: I'm looking for students in vision, robot learning, & AI4Science. Details👇

Why do diverse ANNs resemble brain representations? Check out our new paper with Colton Casto, Noga Zaslavsky, Colin Conwell, Mark Richardson MD PhD, & Ev (like in 'evidence', not Eve) Fedorenko 🇺🇦 on “Universality of representation in biological and artificial neural networks.” 🧠🤖 tinyurl.com/yckndmjt (1/n)

Excited by this ‘tantalizing possibility’ of directly optimizing on brain data—curious to see how this denser, richer supervision signal might broaden capabilities compared to what sparse category- or instance-level labels can achieve

🧵 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

In case it's of interest, here are links to the technical details behind each topic: 1. NeuroAgents research program: tinyurl.com/yc48bnz4 & talk here: youtube.com/watch?v=9_7mQu… 2. NeuroAI Turing Test (with Jenelle Feather, Meenakshi Khosla, and Apurva Ratan Murty):

If you’re at ICLR 2026, check out Ammar’s spotlight paper “Sparse Components Distinguish Visual Pathways & Their Alignment to Neural Networks” — where he uses Bayesian NMF to reveal dominant components specific to each visual stream (ventral/dorsal/lateral) and introduces a new

Announcement: Workshop at #CCN2025 🧠 Modeling the Physical Brain: Spatial Organization & Biophysical Constraints 🗓️ Monday, Aug 11 | 🕦 11:30–18:00 CET |📍 Room A2.07 🔗 Register: tinyurl.com/CCN-physical-b… #NeuroAI CogCompNeuro

Check out Chaitanya Kapoor 's super thorough work on how representational convergence changes across depth, across training, and across distribution shifts—across DCNNs, self-supervised models, ViTs, and LLMs. He’s also building new metrics for alignment—definitely someone worth

✨New edition of our community-building workshop series!✨ Tomorrow at #CVPR2025, we invite speakers to share their stories, values, and approaches for navigating a crowded and evolving field, especially for early-career researchers. Cheeky title🤭: How to Stand Out in the

My dear friend/nanny just lost her husband to a sudden medical emergency. She’s alone here with her 4-year-old, with no safety/financial net. Please consider donating or sharing gofund.me/f3c45e41

Super excited to share our new article: “Dissociable cortical regions represent things and stuff in the human brain” with Nancy Kanwisher @[email protected], Pramod RT/ಪ್ರಮೋದ್ ರಾ ತಾ and Josh Tenenbaum Video Abstract: youtube.com/watch?v=B0XRG_… Paper: authors.elsevier.com/a/1lWxv3QW8SA3…