To view publications by project, click the buttons down below:
2026
- SenSys
“ApproxBit: Efficient Video Analytics through Latency-Aware Offloading with Learned Binary Codes,” Resilient AI
Hyunseung Kim, Sheetal Prasanna; Yin Li (U of Wisconsin at Madison); Somali Chaterji, and Saurabh Bagchi. To appear at the ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems (SenSys), pp. 1-14, May 2026. (Acceptance rate: 52/263 = 19.8% (Round in November)). [ Video demo ]
2025
- NeurIPS
“CAMILA: Context-Aware Masking for Image Editing with Language Alignment,” Resilient AI Hyunseung Kim; Chiho Choi, Srikanth Malla, Sai Prahladh Padmanabhan (Samsung USA); Saurabh Bagchi; Joon Hee Choi (Samsung). Accepted to appear at 39th Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 1-13, December 2-7, 2025. (Acceptance rate: 5,290/21,575 = 24.5%) - ICCV
“Learning to inference adaptively for multimodal large language models,” Resilient AI Zhuoyan Xu, Khoi Duc Nguyen (University of Wisconsin at Madison); Preeti Mukherjee, Saurabh Bagchi, Somali Chaterji; Yingyu Liang, and Yin Li (University of Wisconsin at Madison). Appeared at the International Conference on Computer Vision (ICCV), pp. 3552-3563, October 19-23, 2025. (Acceptance rate: 2,698/11,152 = 24.2%) - UAI
“Root Cause Analysis of Failures from Partial Causal Structures,” Resilient AI
Azam Ikram, Kenneth Lee (Joint first authors); Shubham Agarwal, Shiv Kumar Saini (Adobe Research); Saurabh Bagchi, and Murat Kocaoglu. In The 41st Conference on Uncertainty in Artificial Intelligence (UAI), pp. 1-12, July 21-25, 2025. (Acceptance rate: 230/750 = 30.7%)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
2005
2004
2003
Copyright notice: Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional
purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work
in other works must be obtained from the appropriate publisher (IEEE, ACM, Elsevier, etc.)
purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work
in other works must be obtained from the appropriate publisher (IEEE, ACM, Elsevier, etc.)