3 papers
cs.CV2025
Semantic Compression of 3D Objects for Open and Collaborative Virtual Worlds
Jordan Dotzel, Tony Montes, Mohamed S. Abdelfattah +1
Traditional methods for 3D object compression operate only on structural information within the object vertices, polygons, and textures. These methods are effective at compression…
cs.LG2025
SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs
Ahmed F. AbouElhamayed, Jordan Dotzel, Yash Akhauri +6
Large language models have high compute, latency, and memory requirements. While specialized accelerators such as GPUs and TPUs typically run these workloads, CPUs are more widely…
cs.LG2024
ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models
Yash Akhauri, Ahmed F AbouElhamayed, Jordan Dotzel +4
The high power consumption and latency-sensitive deployments of large language models (LLMs) have motivated efficiency techniques like quantization and sparsity. Contextual sparsit…