Greg Schoeninger

ArXiv Dives - Lumiere

ArXiv Dives - Depth Anything

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