🔥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

New paper from IDSIA motivated by building an artificial scientist with World Models! A key idea is to get controller C to generate pure thought experiments in form of *weight matrices* of RNNs that still surprise the world model M, and then updating it. arxiv.org/abs/2212.14374

lol, draft of full GPT-4 paper with architecture and data details is already leaked on torrent😂 The vision component in the architecture is an interesting twist to plain ViT, and scaled up quite a bit! Link to the torrent for the curious: assets.speakcdn.com/assets/2703/bu…

To celebrate David Deutsch’s 70th birthday, colleagues and friends of David have contributed text and videos in which they share ideas on physics and philosophy related to David’s work: dd70th.weebly.com

Pleasant surprise of ICML Conference: There is a growing Weight Space Learning Community out there - it was great to meet you all: Haggai Maron (Haggai Maron), Gal Chechik (Gal Chechik), Konstantin Schürholt (Konstantin Schürholt), Eliahu Horwitz (Eliahu Horwitz), Derek Lim (Derek Lim),

Had a great time presenting at #ICML2024 alongside Vincent Herrmann & Louis Kirsch. But the true highlight was Jürgen Schmidhuber himself capturing our moments on camera! #AI #DeepLearning

Have you ever wondered what happens when you reduce a story to a low-dimensional latent representation? Well my new IEEE TPAMI work with Vincent Herrmann, Zachary Friggstad, and Jürgen Schmidhuber shows that it has some pretty cool applications 🎉 Check it out: doi.org/10.1109/TPAMI.… (1/n)

Since 1990, we have worked on artificial curiosity & measuring „interestingness.“ Our new ICML paper uses "Prediction of Hidden Units" loss to quantify in-context computational complexity in sequence models. It can tell boring from interesting tasks and predict correct reasoning.