Mohammad Rastegari

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

Speculative Streaming: Fast LLM Inference without Auxiliary Models

LazyLLM: DYNAMIC TOKEN PRUNING FOR EFFICIENT LONG CONTEXT LLM INFERENCE

KV Prediction for Improved Time to First Token

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

(Dynamic) Prompting might be all you need to repair Compressed LLMs

Label-efficient Training of Small Task-specific Models by Leveraging Vision Foundation Models

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding

CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement