Scientists have taken holograms one step further by adding the sense of touch. ow.ly/82nB50Gdmt8

It is widely claimed that DNNs are the “best” models of human vision. Our article entitled “Deep Problems with Neural Network Models of Human Vision” challenges this view and proposes a way forward. Thread: 1/25 psyarxiv.com/5zf4s/

These 'Beach Animals' were created by Theo Jansen as a fusion of art and engineering. The kinetic structures walk on their own and get all their energy from the wind.

Reality shatter. Our illusory world. The psychology of perception. These boxes are not moving. (GIF by じゃがりきん) x.com/pickover/statu…

!!!! Ok I recorded a (new!) 2h25m lecture on "The spelled-out intro to neural networks and backpropagation: building micrograd" youtube.com/watch?v=VMj-3S… . This is the culmination of about 8 years of obsessing about the best way to explain neural nets and backprop.

Trying to get some work done in this coffee shop but this is happening 7 feet from me. Why can't I be this content?

🪐 Introducing Galactica. A large language model for science. Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more. Explore and get weights: galactica.org

Thought-provocative new paper from Geoffrey Hinton: what if we could replace backpropagation with something better?

2022 saw a whirlwind of neuroAI research. Brain Dall-E. Neurons in a dish playing pong. GPT predicts how brains process language. I read through a bunch of papers so you don't have to. Read my review of 2022. xcorr.net/2023/01/01/202…

BCL 2023: The amalgamation of eminent speakers, enthusiastic participants, and vibrant organizers. A photograph to remember ✌️

With one line of Python code, Cleanlab can: • Find mislabeled data + train a robust model • Detect outliers and out-of-distribution samples • Analyze multi-annotator data + quality of labelers • Suggest which data to label next (active learning) 4 of 5

Really excited to present new work by Rita González Márquez @ritagonmar.bsky.social: we visualized the entire PubMed library, 21 million biomedical and life science papers, and learned a lot about -- THE LANDSCAPE OF BIOMEDICAL RESEARCH biorxiv.org/content/10.110… Joint work with @CellTypist and Ben Schmidt / @[email protected]. 1/n

Please RT!! We will hold a free online interdisciplinary workshop on #MachineLearning and theory development on July 10-12 (three half days), with excellent speakers from psychology, neuroscience, sociology, cognitive science etc. Please register here. ml-theory.com

On caring mindingourway.com/on-caring/

🦟 By infusing a virtual fruit fly with artificial intelligence, HHMI | Janelia and Google DeepMind scientists have created a computerized insect that can walk and fly just like the real thing. 🤖 🔗janelia.org/news/artificia…

Be a content creator for the Neuromatch NeuroAI course! We're looking for people to write tutorials on transfer learning and RL in PyTorch over the next 3 weeks. If you want to help build this amazing course, DM me for details or fill out this app: airtable.com/app32npl2ZlbJv…

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

Introducing Continuous Thought Machines New Blog: sakana.ai/ctm/ Modern AI is powerful, but it’s still distinct from human-like flexible intelligence. We believe neural timing is key. Our Continuous Thought Machine is built from the ground up to use neural dynamics as

🧠 Janelia researchers have developed a new way to map how individual connections between neurons change across the entire brain during learning, giving scientists a new view into how changes in behavior show up in the brain. janelia.org/news/new-imagi…

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: sakana.ai/rlt Paper: arxiv.org/abs/2506.08388 Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and