Arham Khan

According to our database, Arham Khan authored at least 6 papers in 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism.

Mansi Sakarvadia, Arham Khan, Aswathy Ajith, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian T. Foster

CoRR, 2023

OpenHLS: High-Level Synthesis for Low-Latency Deep Neural Networks for Experimental Science.

Maksim Levental, Arham Khan, Ryan Chard, Kazutomo Yoshii, Kyle Chard, Ian T. Foster

CoRR, 2023

LibPressio-Predict: Flexible and Fast Infrastructure For Inferring Compression Performance.

Robert Underwood, Sheng Di, Sian Jin, Md Hasanur Rahman, Arham Khan, Franck Cappello

Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, 2023

SECRE: Surrogate-Based Error-Controlled Lossy Compression Ratio Estimation Framework.

Arham Khan, Sheng Di, Kai Zhao, Jinyang Liu, Kyle Chard, Ian T. Foster, Franck Cappello

Proceedings of the 30th IEEE International Conference on High Performance Computing, 2023

An Efficient and Accurate Compression Ratio Estimation Model for SZx.

Arham Khan, Sheng Di, Kai Zhao, Jinyang Liu, Kyle Chard, Ian T. Foster, Franck Cappello

Proceedings of the IEEE International Conference on Cluster Computing, 2023

Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models.

Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian T. Foster

Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, 2023