◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Arash Bakhtiari

Microsoft

7 papers hereh-index 82.6k citations18 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author4

Across the 4 of 7 papers where every author was matched, so the position is known.

fields
  • cs.CL3
  • cs.LG2
  • astro-ph.IM1
  • cs.PF1
affiliations
  • Microsoft
Homepage

identity via Semantic Scholar / OpenAlex

activity
20202025
most citedLarq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks

21 citations · 31 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2024★ 3 cited

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design

Haojun Xia, Zhen Zheng, Xiaoxia Wu +10

Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing…

cs.LG2020★ 21 cited

Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks

Tom Bannink, Arash Bakhtiari, Adam Hillier +5

We introduce Larq Compute Engine, the world's fastest Binarized Neural Network (BNN) inference engine, and use this framework to investigate several important questions about the e…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.