Salman Asif

M. Salman Asif Associate Professor Department of Electrical and Computer Engineering Cooperating Faculty Department of Computer Science and Engineering University of California, Riverside Email: sasif@ucr.edu Phone: (951) 827-2385 Office: 4126 Multidisciplinary Research Building (MRB) Mail: 900 University Ave., Riverside, CA 92521 Web: www.ece.ucr.edu/~sasif Google Scholar profile

I am an Associate Professor in the Department of Electrical and Computer Engineering at the University of California, Riverside.

Research interests. My research interests broadly lie in the areas of computational imaging, signal/image processing, computer vision, and machine learning. I design algorithms to learn and exploit latent signal structures for fast and efficient information recovery.

Current research focus is on computational imaging (physics-based and data-driven approaches), adversarial attacks and defenses for robust computer vision, multi-task and multi-modal machine learning, and wearable sensors for health monitoring and rehabilitation.

News and updates

• Targeted unlearning with single layer unlearning gradient (SLUG) accepted to ICML. Congratulations Zikui and Yaoteng!

  • Targeted Unlearning with Single Layer Unlearning Gradient

  • More information and code available at https:github.com/CSIPlab/SLUG

• One paper on robust multimodal learning accepted to IEEE TPAMI. Congratulations Kaykobad!

  • Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation

• We received a DARPA AIE award for DISCO: Discovery of Sparsity-Constrained Optimization Algorithms with Chinmay Hegde, NYU.

• We received an NSF SCH grant for Comprehensive Tissue Disease Diagnosis Using a Multimodal Robotic System.
  This is a collaborative project across UCR (with Jun Sheng and Chen Li), UCSD (Sheng Xu), and City of Hope (Mustafa Raoof).
  More information can be found here.

• One paper on multimodal unlearning accepted to EMNLP Findings

  • Cross-Modal Safety Alignment: Is textual unlearning all you need?

• One preprint on Unlearning Targeted Information via Single Layer Unlearning Gradient with Zikui Cai, Yaoteng Tan
  Code available at https:github.com/CSIPlab/SLUG

• Happy to serve as Area Chair for CVPR 2025, ICLR 2025, and WACV 2025; Senior Program Committee Member for AAAI 2025

• One paper on transformer-based event cameras accepted to ECCV 2024. Congratulations Bin and Zhan!

  • Transformer-Based Event Denoising Across Varied Noise Levels

• One paper accepted to IEEE Journal of Selected Topics in Signal Processing.

  • DoDo: Double DOE Optical System for Multishot Spectral Imaging

• One paper accepted to ICML 2024

  • Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis

• One paper accepted to IEEE Open Journal on Signal Processing

  • Multimodal Transformer for Material Segmentation

• One paper accepted to IEEE TCI. Congratulations Nebiyou and Bek!

  • Domain Expansion via Network Adaptation for Solving Inverse Problems

• One paper accepted to CVPR 2024. Congratulations Qi and Zhan!

  • PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos

• One paper presented in AAAI 2024. Congratulations Zikui and collaborators!

  • Disguise without Disruption: Utility-Preserving Face De-Identification

• One paper accepted to IEEE TPAMI. Congratulations Zhihao and Zhan!

  • Efficient Visual Computing with Camera RAW Snapshots

• more news