Sublime

Meta presents MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts - Dividesy expert modules into modality-specific groups - Achieves better performance than the baseline MoE abs: https://t.co/aXWVr0plp9 alphaxiv:... See more

Notebooks for Lecture 5 on Recommendation on Graphs Lab1: Google PageRank https://t.co/WtbFZdzmou Lab2: Collaborative/low-rank recom https://t.co/QdRsseuSAd Lab3: Content/graph-Dirichlet... See more

SAPG: Split and Aggregate Policy Gradients Significantly higher performance across a variety of challenging environments where vanilla PPO and other strong baselines fail to achieve high performance proj: https://t.co/HGFlqF8p8J abs: https://t.co/oixKLELgji... See more

3. Machine Learning for Beginners This covers and helps you learn: - Various ML Techniques - Building your first ML Project right from data collection to create a web app for a trained model - NLP Techniques - Times Series -... See more

My lecture notes on regularization techniques in machine learning https://t.co/27tRxkieYx Check out the section on double descent suggested by @ylecun :) https://t.co/s7JPRPEHCP