Pushkar Shukla
पुष्कर शुक्ला

I am a PhD student at the Toyota Technolgical Institute at Chicago working under the supervision of Dr. Matthew Turk. I work at the intersection of fairness, computer vision, and interpretability. My research broadly focuses on different aspects of Safe AI, including but not limited to bias detection and mitigation, counterfactual causal analysis, and safety evaluations. I am passionate about building solutions that bridge the gap between ethical AI development and practical applications.
Previously, I completed my Masters in Computer Science from University of California, Santa Barbara where I closely worked with Dr. William Wang on Goal-Oriented Visual Dialogue. Long back as an undergrad and then as a young reseacher I spent seven transformative years in the charming town of Roorkee, in Northern India. Those years were incredibly formative, leaving a lasting impact on my personal growth and shaping the person I am today.
When I’m not diving into research, you’ll probably find me trying out new recipes in the kitchen—experimenting with different flavors or enjoying a run/walk/hike outdoors.
You can find my curriculum vitae here.
news
Mar 12, 2025 |
|
---|---|
Jan 29, 2025 |
|
Jan 14, 2025 |
|
Sep 30, 2024 |
|
Jul 16, 2024 |
|
selected publications
- CVPR-W 2023CAVLI - Using Image Associations To Produce Local Concept-Based ExplanationsIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2023
- AAAI 2021Text-based rl agents with commonsense knowledge: New challenges, environments and baselinesIn Proceedings of the AAAI Conference on Artificial Intelligence, Jun 2021
- ACL 2019What should I ask? using conversationally informative rewards for goal-oriented visual dialogACL 2019, Jun 2019
- ETRA 20183D gaze estimation in the scene volume with a head-mounted eye trackerIn Proceedings of the Workshop on Communication by Gaze Interaction, Jun 2018
- CVPR-W 2018Automatic cricket highlight generation using event-driven and excitement-based featuresIn Proceedings of the IEEE conference on computer vision and pattern recognition workshops, Jun 2018
- ICCV-W 2017A computer vision framework for detecting and preventing human-elephant collisionsIn Proceedings of the IEEE international conference on computer vision workshops, Jun 2017
- WACV 2017A deep learning frame-work for recognizing developmental disordersIn 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Jun 2017
patents
- US PatentAutomated health condition scoring in telehealth encountersIn US Patent App. 16/949,370, 2021
preprints
- Preprint
- Preprint
- PreprintEnhancing text-based reinforcement learning agents with commonsense knowledgearXiv preprint arXiv:2005.00811, 2020