The sensitivity of DNNs to adversarial attacks has long been thought to be an "Achilles heel" that will ultimately make them unsafe in real-world applications. Has this sensitivity changed as DNNs have scaled-up and rivaled or beat human-level accuracy? serre-lab.github.io/Adversarial-Al…

Just how does AI distinguish one object from another? A team at Carney has developed a new approach to understanding computer vision, which can be used to help create better, safer and more robust artificial intelligence systems. Read more @ bit.ly/CarneyCRAFT

How does your blue compare to others'? I implemented a new feature on ismy.blue to compare against a database of hundreds of people who took the test.

Amazing talk by Li Zhaoping (Li Zhaoping) on: "Looking and Seeing through a Bottleneck: a VBC Framework for Vision, from the Perspective of Primary Visual Cortex" See her 2024 paper "Peripheral vision is mainly for looking rather than seeing": sciencedirect.com/science/articl…

[video] Aligning deep networks with human vision will require novel neural architectures, data diets and training algorithms Thomas Serre, Brown University cbmm.mit.edu/video/aligning…

Finally finish making our website GrowAIlikeAChild growing-ai-like-a-child.github.io 🙌 with William Yijiang Li Dezhi Luo Martin Ziqiao Ma Zory Zhang Pinyuan Feng (Tony) Pooyan Rahmanzadehgervi and many others 🚶🚶‍♂️🚶‍♀️

Congrats to Columbia University scientist Paul Linton who received the David Marr Medal from the Applied Vision Association for "pioneering research on visual experience." 🏆👁️🧠

#ICML #cognition #GrowAI We spent 2 years carefully curated every single experiment (i.e. object permanence, A-not-B task, visual cliff task) in this dataset (total: 1503 classic experiments spanning 12 core cognitive concepts). We spent another year to get 230 MLLMs evaluated

I have been long arguing that a world model is NOT about generating videos, but IS about simulating all possibilities of the world to serve as a sandbox for general-purpose reasoning via thought-experiments. This paper proposes an architecture toward that arxiv.org/abs/2507.05169

Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research🧵

Ready to present your latest work? The Call for Papers for #UniReps2025 NeurIPS Conference 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: Danica Sutherland David Alvarez Melis Nikolaus Kriegeskorte

I’m Shawn, founder of Memories.ai, former researcher at Meta and CS PhD at University of Cambridge. Today we’re launching Memories.ai: we built the world’s first Large Visual Memory Model - to give AI human-like visual memories. Why visual memory? AI to

Collaborations are moving neuroscience forward. Scientists from 20 institutions (including ours!) created the first brain-wide map of individual neurons’ activity in mice for the International Brain Laboratory. Video from SWC sainsburywellcome.org/web/research-n…

DeepSeek’s paper “DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning” was featured on the cover of Nature, with the company’s CEO Wenfeng Liang as the corresponding author.

Great to present my work "Five Illusions Challenge Our Understanding of Visual Experience" at the European Conference on Visual Perception (#ECVP2025) Project Website + Preprint in link below 👇 The Italian Academy Nikolaus Kriegeskorte Columbia University's Zuckerman Institute Center for Science and Society Columbia Science

Encoding models predict visual responses to novel images in cortical areas. But can these models offer new insights about categorical representations? If so, we should be able to generate new hypotheses from them to be tested in future experiments. NeurIPS Conference #NeurIPS2025 1/15