Pinned
Dileep George
5,945 posts
Dileep George
@dileeplearning
Head of AI @AsteraInstitute Prev: AGI @DeepMind, cofounder @vicariousai (acqd by Alphabet), cofounder @Numenta. IIT-Bombay, MS&PhD Stanford. agicomics.net
I love Andrej...but this makes no sense to me. I don't see how converting text to image ('pixels') makes it any better for language modeling. What am I missing?I quite like the new DeepSeek-OCR paper. It's a good OCR model (maybe a bit worse than dots), and yes data collection etc., but anyway it doesn't matter. The more interesting part for me (esp as a computer vision at heart who is temporarily masquerading as a natural language- Location, encoded by place cells, is important for animals, humans, … and airplanes. Check out our new work: "Space is a latent sequence”. It will change the way you look at place cells, spatial representations, remapping, and knowledge transfer. 🧵 arxiv.org/pdf/2212.01508…
GIF - Bing is super smart. It found the link between LinkedIn and SVB collapse....see, the name had the link in it 😇
- Hippocampus is phenomena-rich, all confusing! What if they arise from the wrong space-centric view? We offer a different story of how space is represented in the brain * there are no place cells! cognitive map is not spatial! * Kant is wrong, Leibniz is right! * place field
- We study bias-variance dilemma in class, but reading the paper gives important historical perspective. You'll see that many of the 'unreasonable effectiveness' and 'surprising findings' are predicted in this paper. Thread..(1) dam.brown.edu/people/geman/H…
- I agree with @ylecunYann LeCun says LLMs are not a bubble in value or investment; they will power many useful apps and justify big infra The bubble is believing LLMs alone will reach human-level intelligence Progress needs breakthroughs, not just more data/compute "we're missing something big"
00:00 - Yes, a neuroscientist can understand a microprocessor...a rebuttal thread on the popular paper by @stochastician and @KordingLab While I agree with some of the points, I worry the paper leaves a misleading impression about neuroscience experiments 1/23
- Some answers from chatGPT are deliciously, mind-bogglingly, out-of-this-world good! 🤯🤯
Satya, to tell the truth, made a search engine that is full of asatya. 😇 - Excited to have this out! A blog and tweet thread to follow soon...
- In-context learning (ICL) is a fascinating property of transformers. We seek to de-mystify ICL as a combination of 1️⃣ learning template circuits 2️⃣ context-sensitive retrieval of those templates and 3️⃣ rebinding appropriate slots in the templates. 🧵 1/N arxiv.org/abs/2307.01201
- You know English. You don’t know Malayalam. You decide to learn it by listening to podcasts that are purely in Malayalam. What will happen? A thread about language models, meaning, understanding etc…. Plus, you get to learn Malayalam :-) 1/N
- Hippocampus is not representing locations & cognitive maps are not spatial! Anyone interested in cognitive maps, schemas, or navigation & planning should read this companion blog to our paper science.org/doi/10.1126/sc… It will change your mind! blog.dileeplearning.com/p/space-is-a-s…
