Yannic Kilcher 🇸🇨
@ykilcher
I make videos. Skill > Destiny. vi / vim
🥳Special Video🥳This has been in the works for a while. I used CLIP + BigGAN to make a music video for a song with lyrics made from ImageNet class labels🤠"Be my weasel", performed by me on a looper🎸Code & references available, make your own! Enjoy🤟 youtu.be/rR5_emVeyBk
Join us at 8pm CEST on Discord to chat about ROCK: A variational formulation for occupation kernel methods in Reproducing Kernel Hilbert Spaces. Don't miss it :) discord.gg/QrUDEQXE?event…
in 45 minutes
📢Paper Discussion Live📢 Come tonight to chat with us about: Design Patterns for Securing LLM Agents against Prompt Injections Be there, fun awaits! 6pm UTC, discord.gg/y78WFTy4?event…
📢Paper Discussion Live📢 Come tonight to chat with us about: Design Patterns for Securing LLM Agents against Prompt Injections Be there, fun awaits! 6pm UTC, discord.gg/y78WFTy4?event…
Come chat with us tonight on Discord about Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling 6pm UTC, be there: discord.gg/RPVNUdVu?event…
Come join us tonight on discord for a masterclass on Gaussian Processes. 6pm UTC discord.gg/RPVNUdVu?event…
join us tonight to talk about Adam! maybe we will touch a bit on Muon & friends -- they carry many of the open questions we have about Adam ❤️ thanks Yannic
📢Live Paper Discussion📢 Tonight (8pm CEST) we'll chat with Antonio about "Adam's Secret Sauce". Come join on discord, everyone is welcome! discord.gg/gfnT9CEn?event…
📢Live Paper Discussion📢 Tonight (8pm CEST) we'll chat with Antonio about "Adam's Secret Sauce". Come join on discord, everyone is welcome! discord.gg/gfnT9CEn?event…
Adam is similar to many algorithms, but cannot be effectively replaced by any simpler variant in LMs. The community is starting to get the recipe right, but what is the secret sauce? @gowerrobert and I found that it has to do with the beta parameters and variational inference.…
Statistical Learning Theory Paper Discussion happening right now on discord: ykilcher.com/discord
🎯Live Paper Discussion🎯 Come tonight on Discord to chat about Muon Optimizer - the current record holder in training speed for NanoGPT. Paper presentation first, then paper discussion, then free-for-all after hours ✨ 6pm UTC (8pm CEST, 2pm ET): discord.gg/zD7Ju6PE?event…
Introducing Pageshift AI, the thing I was working on over the last couple of months Generate your own audiobook, with just a simple prompt or listen to an existing one from the community pageshift.ai (Currently only really working on desktop end devices)
📢Live Paper Discussion📢 Tonight on Discord, Francesco will present Oniris: Autoregressive and Sample-Efficient Next-Gen Video Diffusion. Come join, everyone is welcome: 6pm UTC, discord.gg/tc6eT4Zy?event…
Me and @MozarellaPesto made this model called Oniris with 0$ in funding: It is an efficient autoregressive world-model. We are starting to build in the open today. Turns out, we can improve current methods by making the training sample efficient.
📢Paper Discussion Live📢 Tonight, we are talking about: Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula Come join us, 6pm UTC: discord.gg/4Td2YmFH?event…
📅Saturday Night Paper Discussion📅 Join us tonight to talk about d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning 6pm UTC on Discord, no prior knowledge required: discord.gg/ec2FXBFA?event…
Nothing says believe me quite like an article that you write about yourself saying how believable you are.
He’s been spreading false information about us. We’re actually getting ready to build the best-equipped nonprofit the world has ever seen – we’re not converting it away. More info here: openai.com/index/nonprofi…
🔥Live Paper Discussion 🔥 Tonight on Discord, we'll chat about "Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space". Come join, 6pm UTC: discord.gg/brkRa9Fz?event…
📅 Event Tonight 📅 Join us on Discord for a masterclass on Optimization over Polynomials (Semialgebraic Optimization). Be there, 7pm UTC: discord.gg/SszceUKS?event…
Starting in 9 minutes! Our Saturday paper talk about: Approximation Theory and Approximation Practice, Extended Edition Come join us, now: ykilcher.com/discord
🚨 NEW PAPER DROP! Wouldn't it be nice if LLMs could spot and correct their own mistakes? And what if we could do so directly from pre-training, without any SFT or RL? We present a new class of discrete diffusion models, called GIDD, that are able to do just that: 🧵1/12
Come join our Saturday Discord Paper Talk! 🚀 Today we're talking about: Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution. 7pm UTC (in 15mins from this post) here: discord.gg/VeDnz87d?event…
Come chat with us tonight! We're discussing the paper: Large Concept Models: Language Modeling in a Sentence Representation Space 7pm UTC (1h from now): discord.gg/qyTRhyEN?event…
