Pinned
AI is a form of empirical philosophy. I bet that if Plato, Phyrro, Descartes or Wittgenstein were around now, they’d be tinkering with neural networks. With language models, with generative models and with agents.
Ali Eslami
1,036 posts
Ali Eslami
@arkitus
- Now for something different! Deep RL + GAN training + CelebA = artificial caricature. Agents learn to draw simplified (artistic?) portraits via trial and error. @ #NeurIPS2019 creativity workshop. Animated paper: learning-to-paint.github.io PDF: arxiv.org/abs/1910.01007 Thread.
00:00 - "Neural scene representation and rendering" now in @ScienceMagazine. By training deep networks to predict what scenes look like from new viewpoints, we get them to understand images: deepmind.com/blog/neural-sc… @DeepSpiker @OriolVinyalsML @theophaneweber @demishassabis
00:00 - Conditional Neural Process implementation by Marta Garnelo! Neural networks meet stochastic processes. Useful for few-shot regression, classification and meta-learning: 1. Repo: github.com/deepmind/condi… 2. Notebook: github.com/deepmind/condi… 3. Paper: arxiv.org/abs/1807.01613
- This started as a prototype we built back in March 2024 which we called ‘Neural Google’. The core idea: wrap Gemini around Google and let it do the searching for you.
00:00 - Gemini 2.5 Pro just got even better at code ✨ #1 on LMArena with 1448 Elo, #1 on WebDev Arena with 1420 Elo. Also SOTA for video, with 84.8% on VideoMME. @TimBettridge vibe-coded a 3D tour of the Art Institute of Chicago's collection with it, right in @GeminiApp Canvas 🎨
00:00 - Notebooks for Neural Processes (NPs) and Attentive Neural Processes (ANPs) now available. Compared to CNPs (published last year): 1. NPs model the function with a global latent, and 2. ANPs fit the data better. Kudos to @hyunjik11 and Marta Garnelo et al! github.com/deepmind/neura…
- Getting closer to the dream! A network that uses unlabelled images to boost performance when labels are scarce (new SOTA), and it's no worse than ResNet when labels are plentiful. Also: Unsupervised net + just a linear on top outperforms original AlexNet! arxiv.org/abs/1905.09272
- Introducing PolyGen: an autoregressive model of 3D meshes. arxiv.org/abs/2002.10880 Transformers + Pointer Nets = train on raw mesh data (i.e. variable-length lists of vertices and faces). No need to voxelise or rasterise! with @charlietcnash @yaroslav_ganin @PeterWBattaglia
00:00 - better late than never lots of rough edges still but the team is grinding do share feedback github.com/google-gemini/…
- 10 years ago I didn't think I'd see this in my lifetime. Welcome to the future.
- Clean and performant PyTorch implementation of Generative Query Networks by Shohei Taniguchi: github.com/iShohei220/tor… Pixyz implementation by Shohei Taniguchi and Masahiro Suzuki: github.com/masa-su/pixyzo… Pixyz (deep generative modeling library): github.com/masa-su/pixyz 👌
- Genie 3 is the most impressive AI demo I've seen since ChatGPT. In 2016 we were working on 'Neural Representation and Rendering' and could already see a vague path to this. But I didn’t think it’d happen so soon.
00:00
