Mohamed S. Abdelfattah

FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion

UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs

Regression Language Models for Code

TokenButler: Token Importance is Predictable

xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models

Overfill: Two-Stage Models for Efficient Language Model Decoding

Palu: KV-Cache Compression with Low-Rank Projection