Greg Schoeninger

Arxiv Dives - Toolformer: Language models can teach themselves to use tools

Arxiv Dives - Self-Rewarding Language Models

Arxiv Dives - Direct Preference Optimization (DPO)

Arxiv Dives - Efficient Streaming Language Models with Attention Sinks

Arxiv Dives - How Mixture of Experts works with Mixtral 8x7B

Arxiv Dives - LLaVA 🌋 an open source Large Multimodal Model (LMM)