Shervin Malmasi

Researcher, Amazon

Joined

July 2019

Names

Shervin Malmasi

Emails

****@mq.edu.au (Confirmed)

,

****@amazon.com (Confirmed)

Personal Links

Semantic Scholar

Career & Education History

Researcher

Amazon (amazon.com)

2018 – Present

Advisors, Relations & Conflicts

PhD Advisor

Present

Expertise

No areas of expertise listed

Publications

Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction
Theodore Glavas, Nikhita Vedula, Dushyanta Dhyani, Yilun Zhu, Shervin Malmasi
- ACL Findings 2026
- Readers: Everyone
A Modular LLM Framework for Explainable Price Outlier Detection
Shadi Sartipi, John Wu, Sina Ghotbi, Nikhita Vedula, Shervin Malmasi
- ICLR 2026 Workshop Advances in Financial AI
- Readers: Everyone
Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization
Kalle Kujanpää, Yuying Zhu, Kristina Lisa Klinkner, Shervin Malmasi
- ICLR 2026 Workshop AIMS
- Readers: Everyone
Bridging the gap between information seeking and product search systems: Q&A recommendation for e-commerce
Saar Kuzi, Shervin Malmasi
- OpenReview Archive Direct Upload
- Readers: Everyone
Ambiguity detection and uncertainty calibration for question answering with large language models
Zhengyan Shi, Giuseppe Castellucci, Simone Filice, Saar Kuzi, Elad Kravi, Eugene Agichtein, Oleg Rokhlenko, Shervin Malmasi
- OpenReview Archive Direct Upload
- Readers: Everyone
Intra-Prompt Parallel Decoding for Common-Context Question Answering
Theodore Glavas, Nikhita Vedula, Dushyanta Dhyani, Antonios Valkanas, Yilun Zhu, Shervin Malmasi
- Submitted to ICLR 2026
- Readers: Everyone
Wizard of Tasks: A Novel Conversational Dataset for Solving Real-world Tasks in Conversational Settings
Jason Ingyu Choi, Saar Kuzi, Nikhita Vedula, Jie Zhao, Giuseppe Castellucci, Marcus D. Collins, Shervin Malmasi, Oleg Rokhlenko, Eugene Agichtein
- 18 Dec 2023 (modified: 18 Dec 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition
Besnik Fetahu, Zhiyu Chen, Sudipta Kar, Oleg Rokhlenko, Shervin Malmasi
- EMNLP 2023 Findings
- Readers: Everyone
A Simple Loss Function for Convergent Algorithm Synthesis using RNNs
Alexandre Salle, Shervin Malmasi
- 01 Mar 2023 (modified: 06 Jun 2023)
- Submitted to Tiny Papers @ ICLR 2023
- Readers: Everyone
Predicting the Type and Target of Offensive Posts in Social Media
Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, Ritesh Kumar
- 2019 (modified: 12 Nov 2022)
- NAACL-HLT (1) 2019
- Readers: Everyone

View all 15 publications

Co-Authors

View all 34 co-authors