[2312.11514] LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Measuring Massive Multitask Language Understanding

Elo Uncovered: Robustness and Best Practices in Language Model Evaluation

VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactment