Why do powerful AIs like GPT-4 struggle with tasks humans find easy? Dive into GAIA, the game-changing benchmark from Yann LeCun's team, and discover how it redefines the true capabilities of a General AI Assistant beyond standard tests. A must-read for anyone in AI.
Dive into ChatEval, an easy-to-understand multi-agent LLM framework from ICLR 2024. Learn how multiple LLM agents with unique personas debate to evaluate model outputs. An ideal starting point for understanding multi-agent systems.
Discover Meta's Branch-Train-MiX (BTX), a powerful Mixture-of-Experts (MoE) technique. Learn how it merges multiple expert LLMs into one model, solving distributed training bottlenecks and preventing catastrophic forgetting.
Learn about Sparse Upcycling, a Google Research technique for converting dense models into efficient Mixture-of-Experts (MoE). Discover how to boost AI performance and reduce training costs by leveraging existing checkpoints instead of training from scratch.
Discover Direct Preference Optimization (DPO), a simpler and more efficient method for fine-tuning LLMs. Learn how DPO improves upon complex RLHF by eliminating the need for a reward model and using direct supervised learning for more stable and effective results.
Explore the 3 stages of LLM training. This guide breaks down Pre-Training, Supervised Fine-Tuning (SFT), and how Reinforcement Learning from Human Feedback (RLHF) creates more helpful and aligned AI.
Notes from an AACL 2022 tutorial: what BERT's layers learn, why sentence embeddings need contrastive learning, and how PEFT like LoRA fine-tunes huge models cheaply.
