🔥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

CDS Professor Yann LeCun sees the end of large language models, claiming they'll be obsolete in five years. In Newsweek, he explains why current AI lacks real-world understanding—and what a smarter system could look like.   newsweek.com/ai-impact-inte…

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks thrilled to share our #ICML2025 paper led by Walter Mayor-Toro & Johan S. Obando 👍🏽 , with Aaron Courville , where we explore how data collection affects agents in parallelized setups. 1/

New preprint! 🧠🤖 How do we build neural decoders that are: ⚡️ fast enough for real-time use 🎯 accurate across diverse tasks 🌍 generalizable to new sessions, subjects, and species? We present POSSM, a hybrid SSM architecture that optimizes for all three of these axes! 🧵1/7

(1/n)🚨You can train a model solving DFT for any geometry almost without training data!🚨 Introducing Self-Refining Training for Amortized Density Functional Theory — a variational framework for learning a DFT solver that predicts the ground-state solutions for different

Excited that our paper "Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization" was accepted to ICML 2025! We show how Preference Optimization can reduce the impact of noisy concept labels in CBMs. 🧵/9

Excited to share the results of my internship research with AI at Meta, as part of a larger world modeling release! What subtle shortcuts are VideoLLMs taking on spatio-temporal questions? And how can we instead curate shortcut-robust examples at a large-scale? Details 👇🔬

Tired of tuning hyperparameters? Introducing PyLO! We’re bringing hyperparameter-free learned optimizers to PyTorch with drop in torch.optim support and faster step times thanks to our custom cuda kernels. Check out our code here: github.com/Belilovsky-Lab…

To help computational cognitive scientist engage with more naturalistic experiments, I've made NiceWebRL. NiceWebRL is a Python library for designing human subject experiments that leverage machine reinforcement learning environments. github.com/KempnerInstitu…

🚨 Excited to share our new work: "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning"! 📈 We propose gradient interventions that enable stable, scalable learning, achieving significant performance gains across agents and environments! Details below 👇

🚨 Excite to share "Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning" work. 🥳 We tackle gradient instability in large deep RL networks, enabling stable and scalable learning with strong performance across the board. 📄 Paper: arxiv.org/abs/2506.15544