Kushal Kafle

Kushal is a senior research scientist in the vision and language lab (VLL) at Adobe Research. He completed his PhD at Rochester Institute of Technology in 2020, and has been affiliated with Adobe Research since March, 2020.

Kushal’s research focuses on problems at the intersection of vision and natural language processing. Kushal is also interested in bias in machine learning and how to avoid them.

More about Kushal can be found on his personal webpage: https://kushalkafle.com

A complete list of his publications is on Google Scholar. The list below is not updated frequently.

AI & Machine Learning Computer Vision, Imaging & Video Natural Language Processing

Publications

October 19, 2025 International Conference on Computer Vision (ICCV 2025)

Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles

Eric Slyman, Mehrab Tanjim, Kushal Kafle, Stefan Lee

October 19, 2025 International Conference on Computer Vision (ICCV 2025)

Improving Large Vision and Language Models by Learning from a Panel of Peers

Jefferson Hernandez, Jing Shi, Simon Jenni, Vicente Ordonez, Kushal Kafle

June 1, 2025 Association for Computational Linguistics (ACL)

MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities

Savya Khosla, Aditi Tiwari, Kushal Kafle, Simon Jenni, Handong Zhao, John Collomosse, Jing Shi

October 1, 2024 European Conference on Computer Vision (ECCV)

FineMatch: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction

Hang Hua, Jing Shi, Kushal Kafle, Simon Jenni, Daoan Zhang, John Collomosse, Scott Cohen, Jiebo Liu

June 17, 2024 CVPR 2024

FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication

Eric Slyman, Stefan Lee, Scott Cohen, Kushal Kafle

June 17, 2024 CVPR 2024

Building Vision-Language Models on Solid Foundations with Masked Distillation

Sepehr Sameni, Kushal Kafle, Hao Tan, Simon Jenni

January 4, 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Discovering and Mitigating Biases in CLIP-based Image Editing

Mehrab Tanjim, Krishna Kumar Singh, Kushal Kafle, Ritwik Sinha, Garrison W Cottrell

June 22, 2023 CVPR 2023

Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations

Ziyan Yang, Kushal Kafle, Franck Dernoncourt, Vicente Ordonez

November 21, 2022 BMVC 2022

Debiasing Image-to-Image Translation Models

Mehrab Tanjim, Krishna Kumar Singh, Kushal Kafle, Ritwik Sinha, Garrison W Cottrell

March 1, 2020 WACV 2020

Answering Questions About Data Visualizations using Efficient Bimodal Fusion

Kushal Kafle, Robik Shrestha, Brian Price, Scott Cohen, Chris Kanan

June 18, 2018 Conference on Computer Vision and Pattern Recognition (CVPR) 2018

DVQA: Understanding Data Visualization via Question Answering

Kushal Kafle, Scott Cohen, Brian Price, Christopher Kanan

News

Teaching an AI Agent to Retouch Photos: RetouchIQ at CVPR 2026

RetouchIQ is an experimental AI editing agent that understands what you mean when you describe how a photo should look and feel, then translates that intent into precise adjustments in professional photo-editing software.

June 9, 2026

Four Trends at CVPR 2024

Discover the cutting-edge trends in computer vision at CVPR 2024 with a report by Kushal Kafle, Sr. Research Scientist at Adobe Research. Explore the rapid development of large foundation models, multimodality, the pivotal role of data curation, synthetic data generation, and more!

July 23, 2024