Somewhere, something incredible is waiting to be known.
Visitor Counter
| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 23 May 2025 16:57:58 GMT
access-control-allow-origin: *
etag: W/"6830a916-7f6c"
expires: Mon, 29 Dec 2025 11:36:23 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 6791:3946E9:8AE835:9C0CC9:6952655B
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 11:26:23 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210070-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767007583.097639,VS0,VE210
vary: Accept-Encoding
x-fastly-request-id: 4467b66f23b60b337d67128ad85271781f514471
content-length: 8248
Ajay Jaiswal's Homepage
Email
Born is a small town (Belthara) in Eastern UP, India, I got my hands on a computer first time during my undergraduate freshman year.
My journey in computer science began when I was sixteen year old with a fantastic book "Let Us C" by Yashavant Kanetkar. During my career, I have
always tried to make best use of resources and smart people around me to learn and grow. I identified my research potential while working with Prof. Animesh
Mukherjee in IIT Kharagpur and later spent some wonderful time in Samsung Research after graduating. Currently, with the grace of GOD, I am very previlaged
to work and supervised by some extremely brilliant minds in VITA
and AI Health @ UT Austin.
Visitor Counter
Ajay Jaiswal
I am a Ph.D. student at the The University of Texas at Austin working with Prof. Ying Ding, and Prof. Atlas Wang. I am a member of Visual Informatics Group (VITA) @UT Austin. I am also a recipient of Amazon Ph.D. Fellowship. My reseach interest are empirical foundations of machine learning: using rigorous controlled experiments to understand the impact of data, model architecture, and other components of ML pipeline to enable efficient and reliable machine learning systems. During my PhD, I applied this to address several fundamental bottlenecks (efficient and scalable training, fine-tuning and inference) for modern-day neural networks (especially large foundational models and graph neural networks). My research accomplishments are evidenced by several impactful publications in top-tier venues, e.g., NeurIPS, ICML, ICLR, ECCV, ICCV, etc. In the past, I have interned at Apple AIML, Amazon Search, and Adobe Research.
Prior to joining UT Austin, I was a Graduate Student in Computer Science at Indian Institute of Technology, Kharagpur. I was advised by Prof. Animesh Mukherjee and Prof. Pawan Goyal at the CNeRG Lab. I have also spent 3 wonderful years as Lead Research Engineer at Advanced Technology Lab, Samsung Electronics, India under the supervision of Dr. Vijay Narayan Tiwari.
♣ I am currently on the job market looking for industry positions starting April-May 2025. ♣
Recent News
- 09/2024 2 papers (FNN-SkipLLM , C4 Pruning Enough?) accepted to EMNLP Main Track 2024.
- 05/2024 5 papers (JunkDNA, Compressed LLM Trust , Sparse Cocktail, OWL Sparsity , LLM Graph Assistant) accepted to ICML 2024.
- 01/2024 1 paper (LLM-KICK) accepted to ICLR 2024 from internship at Apple.
- 07/2023 1 paper (LLM Essential Sparsity || [Code]) accepted to NeurIPS 2023.
- 07/2023 1 paper accepted to ICCV 2023.
- 05/2023 I joined Apple AI/ML team to work with Yinfei Yang, Zhe Gan, and Xianzhi Du.
- 04/2023 3 papers (2-first authors with one ORAL) accepted to ICML 2023.
- 01/2023 2 papers2 accepted to ICLR 2023.
- 10/2022 1 paper accepted to WACV 2023.
- 09/2022 1 paper accepted to NeurIPS 2022.
- 08/2022 1 paper accepted to ICDM 2022.
- 07/2022 1 paper accepted to ECCV 2022.
- 06/2022 Spending Summer 2022 in Adobe Research as Computational Photography/Computer Vision Intern.
- 05/2022 1 paper accepted to ICML 2022 (Spotlight).
- 01/2022 Awarded Professional Development Fellowship by School of Information, UT Austin
- 08/2021 1 paper accepted to ML4H 2021.
- 07/2021 1 paper accepted to ICDM 2021.
Selected Publication [Full List]
(A superscript * denotes equal contribution)-
[XXXXXX 2025] Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and ObservationsAjay Jaiswal, Jianyu Wang, Yixiao Li, Pingzhi Li, Tianlong Chen, Zhangyang Wang, Chong Wang, Ruoming Pang, Xianzhi Du.[Paper] [Code]
-
[XXXXXX 2025] From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients.Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu, Jiawei Zhao, Yuandong Tian, and Zhangyang Wang.[Paper] [Code] [Blog]
-
[XXXXXX 2025] Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.Zhang, Zhenyu, Ajay Jaiswal, Lu Yin, Shiwei Liu, Jiawei Zhao, Yuandong Tian, and Zhangyang Wang.[Paper] [Code] [Blog]
-
[XXXXXX 2025] Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense FrameworkYuhang Chen, Zhen Tan, Ajay Jaiswal, Huaizhi Qu, Xinyu Zhao, Qi Lin, Yu Cheng, Andrew Kwong, Zhichao Cao, Tianlong Chen.[Paper] [Code]
-
[EMNLP Main 2024] FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping.Ajay Jaiswal, Bodun Hu, Lu Yin, Yeonju Ro, Shiwei Liu, Tianlong Chen, and Aditya Akella.[Paper] [Code]
-
[ICML 2024] LLaGA: Large Language and Graph Assistant.Chen, Runjin, Tong Zhao, Ajay Jaiswal, Neil Shah, and Zhangyang Wang.[Paper] [Code]
-
[ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity.*Lu Yin, *Ajay Jaiswal, Shiwei Liu, Souvik Kundu, and Zhangyang Wang.[Paper] [Code]
-
[ICLR 2024] Compressing llms: The Truth is Rarely Pure and Never Simple.Ajay Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, and Yinfei Yang.[Paper] [Code]
-
[NeurIPS 2023] The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter.Ajay Jaiswal, Shiwei Liu, Tianlong Chen, and Zhangyang Wang.[Paper] [Code]
-
[ICML 2023] Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models.Ajay Jaiswal, Shiwei Liu, Tianlong Chen, Ying Ding, and Zhangyang Wang.[Paper] [Code]
-
[ICML 2023] Graph ladling: Shockingly Simple and Parallel GNN Training without Intermediate Communication.Ajay Jaiswal, Shiwei Liu, Tianlong Chen, Ying Ding, and Zhangyang Wang.[Paper] [Code]
-
[ICLR 2023] Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!Shiwei Liu, Tianlong Chen, Zhenyu Zhang, Xuxi Chen, Tianjin Huang, Ajay Jaiswal, and Zhangyang Wang.[Paper] [Code]
-
[ICLR 2023] Sparse moe as the new dropout: Scaling Dense and self-slimmable transformers.Tianlong Chen, Zhenyu Zhang, Ajay Jaiswal, Shiwei Liu, and Zhangyang Wang.[Paper] [Code]
-
[NeurIPS 2022] Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again.Ajay Jaiswal, Peihao Wang, Tianlong Chen, Justin Rousseau, Ying Ding, and Zhangyang Wang.[Paper] [Code]
-
[ICML 2022] Training Your Sparse Neural Network Better with Any Mask.Ajay Jaiswal, Haoyu Ma, Tianlong Chen, Ying Ding, and Zhangyang Wang.[Paper] [Code]
Teaching & Service
- Workshop Organizer: Edge-Device Large Language Model Competition in conjunction with NeurIPS 2024 [Link].
- Conference Reviewer: TMLR 2024, EMNLP 2024, NeurIPS 2024,2023; ICLR 2024,2023; ICML 2024,2023,2022, ICME 2022/2023, ICDM 2022, KDD 2022.
- Teaching Assistant - OS programming and ML/DS Programming [IIT Kharagpur]
Contact
Address
UTA 5.410
1616 Guadalupe St
Austin, TX
United States
78712
Academic
ajayjaiswal [at] utexas.edu
Other Use
ajayjaiswalhi [at] gmail.com
About Me
Visitor Counter
Copyright © 2022 Ajay Jaiswal. All Rights Reserved.
Powered by UIkit