Purvish Jajal

18 papers A* 1A 5B 1Journal 10Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens.
CoRR
Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiruvathukal, Yung-Hsiang Lu, James C. Davis
2025 A* conf
Detecting Music Performance Errors with Transformers.
AAAI
Benjamin Shiue-Hal Chou, Purvish Jajal, Nicholas John Eliopoulos, Tim Nadolsky, Cheng-Yun Yang, Nikita Ravi, James C. Davis, Kristen Yeon-Ji Yun, Yung-Hsiang Lu
2025 J jnl
Detecting Music Performance Errors with Transformers.
CoRR
Benjamin Shiue-Hal Chou, Purvish Jajal, Nicholas John Eliopoulos, Tim Nadolsky, Cheng-Yun Yang, Nikita Ravi, James C. Davis, Kristen Yeon-Ji Yun, Yung-Hsiang Lu
2025 J jnl
Inference-Time Alignment of Diffusion Models with Evolutionary Algorithms.
CoRR
Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiruvathukal, James C. Davis, Yung-Hsiang Lu
2025 J jnl
LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection.
CoRR
Benjamin Shiue-Hal Chou, Purvish Jajal, Nick John Eliopoulos, James C. Davis, George K. Thiruvathukal, Kristen Yeon-Ji Yun, Yung-Hsiang Lu
2025 A conf
Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge.
WACV
Nicholas John Eliopoulos, Purvish Jajal, James C. Davis, Gaowen Liu, George K. Thiravathukal, Yung-Hsiang Lu
2025 A conf
Token Turing Machines are Efficient Vision Models.
WACV
Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiravathukal, James C. Davis, Yung-Hsiang Lu
2024 B conf
An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions.
ASPDAC
Caleb Tung, Nicholas Eliopoulos, Purvish Jajal, Gowri Ramshankar, Cheng-Yun Yang, Nicholas Synovic, Xuecen Zhang, Vipin Chaudhary, George K. Thiruvathukal, Yung-Hsiang Lu
2024 A conf
Interoperability in Deep Learning: A User Survey and Failure Analysis of ONNX Model Converters.
ISSTA
Purvish Jajal, Wenxin Jiang, Arav Tewari, Erik Kocinare, Joseph Woo, Anusha Sarraf, Yung-Hsiang Lu, George K. Thiruvathukal, James C. Davis
2024 J jnl
Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge.
CoRR
Nick John Eliopoulos, Purvish Jajal, James C. Davis, Gaowen Liu, George K. Thiravathukal, Yung-Hsiang Lu
2024 J jnl
Reusing Deep Learning Models: Challenges and Directions in Software Engineering.
CoRR
James C. Davis, Purvish Jajal, Wenxin Jiang, Taylor R. Schorlemmer, Nicholas Synovic, George K. Thiruvathukal
2024 A conf
Securing Deep Neural Networks on Edge from Membership Inference Attacks Using Trusted Execution Environments.
ISLPED
Cheng-Yun Yang, Gowri Ramshankar, Nicholas Eliopoulos, Purvish Jajal, Sudarshan Nambiar, Evan Miller, Xun Zhang, Dave (Jing) Tian, Shuo-Han Chen, Chiy-Ferng Perng, Yung-Hsiang Lu
2024 J jnl
Token Turing Machines are Efficient Vision Models.
CoRR
Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiravathukal, James C. Davis, Yung-Hsiang Lu
2023 J jnl
An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions.
CoRR
Caleb Tung, Nicholas Eliopoulos, Purvish Jajal, Gowri Ramshankar, Chen-Yung Yang, Nicholas Synovic, Xuecen Zhang, Vipin Chaudhary, George K. Thiruvathukal, Yung-Hsiang Lu
2023 J jnl
Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem.
CoRR
Purvish Jajal, Wenxin Jiang, Arav Tewari, Joseph Woo, Yung-Hsiang Lu, George K. Thiruvathukal, James C. Davis
2023 A conf
PTMTorrent: A Dataset for Mining Open-source Pre-trained Model Packages.
MSR
Wenxin Jiang, Nicholas Synovic, Purvish Jajal, Taylor R. Schorlemmer, Arav Tewari, Bhavesh Pareek, George K. Thiruvathukal, James C. Davis
2023 J jnl
PTMTorrent: A Dataset for Mining Open-source Pre-trained Model Packages.
CoRR
Wenxin Jiang, Nicholas Synovic, Purvish Jajal, Taylor R. Schorlemmer, Arav Tewari, Bhavesh Pareek, George K. Thiruvathukal, James C. Davis
2023 — conf
Reusing Deep Learning Models: Challenges and Directions in Software Engineering.
JVA
James C. Davis, Purvish Jajal, Wenxin Jiang, Taylor R. Schorlemmer, Nicholas Synovic, George K. Thiruvathukal