Akshat Shrivastava

Joined

November 2021

Names

Akshat Shrivastava (Preferred)

Emails

****@fb.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

Semantic Scholar

Career & Education History

Researcher

Facebook (facebook.com)

2019 – 2024

MS student

Department of Computer Science, University of Washington (cs.washington.edu)

2017 – 2019

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Small But Funny: A Feedback-Driven Approach to Humor Distillation
Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Vered Shwartz, Arash Einolghozati
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Readers: Everyone
CoSMoEs: Compact Sparse Mixture of Experts
Patrick Huber, Akshat Shrivastava, Ernie Chang, Chinnadhurai Sankar, Ahmed A Aly, Adithya Sagar
- 4th ALVR Spotlight
- Readers: Everyone
MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts
Xi Victoria Lin, Akshat Shrivastava, Liang Luo, Srini Iyer, Mike Lewis, Gargi Ghosh, Luke Zettlemoyer, Armen Aghajanyan
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Charlie Hou, Akshat Shrivastava, Hongyuan Zhan, Rylan Conway, Trang Le, Adithya Sagar, Giulia Fanti, Daniel Lazar
- PML
- Readers: Everyone
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Charlie Hou, Akshat Shrivastava, Hongyuan Zhan, Rylan Conway, Trang Le, Adithya Sagar, Giulia Fanti, Daniel Lazar
- ICML 2024 Oral
- Readers: Everyone
Treepiece: Faster Semantic Parsing via Tree Tokenization
Sid Wang, Akshat Shrivastava, Aleksandr Livshits
- EMNLP 2023 Findings
- Readers: Everyone
Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
Charlie Hou, Hongyuan Zhan, Akshat Shrivastava, Sid Wang, Aleksandr Livshits, Giulia Fanti, Daniel Lazar
- Published: 04 Mar 2023, Last Modified: 30 Mar 2023
- ICLR 2023 Workshop on Trustworthy ML Poster
- Readers: Everyone

Akshat Shrivastava

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Small But Funny: A Feedback-Driven Approach to Humor Distillation

CoSMoEs: Compact Sparse Mixture of Experts

MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs

Treepiece: Faster Semantic Parsing via Tree Tokenization

Privately Customizing Prefinetuning to Better Match User Data in Federated Learning

Co-Authors