Parsa Kavehzadeh
Scholar

Parsa Kavehzadeh

Google Scholar ID: jSn9dykAAAAJ
Applied Scientist, Dialpad
Natural Language ProcessingMachine LearningData MiningDeep Learning
Citations & Impact
All-time
Citations
287
 
H-index
5
 
i10-index
4
 
Publications
11
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • - Published in top-tier conferences like EACL, EMNLP, and EuroVis
  • - Received recognition such as MVP at Huawei Noah’s Ark Lab
  • - Example publications: UniChart - A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning; S2D - Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models
Research Experience
  • - AI Researcher at Huawei Canada, introduced Sorted LLaMA, a method for integrating nested submodels into a single LLM, and developed a confidence-based early exiting mechanism to accelerate inference.
Education
  • - MSc in Computer Science from York University, supervised by Professor Enamul Hoque, focusing on natural language interactions with visualizations.
  • - BSc in Computer Engineering from Amirkabir University of Technology, exploring deep learning for anomaly detection and text chunking.
Background
  • An NLP researcher specializing in the development and optimization of Large Language Models (LLMs). His research interests include efficient LLM training, inference acceleration, and multi-modal systems integrating NLP and computer vision.
Co-authors
0 total
Co-authors: 0 (list not available)