Hello, I'm Sankalp Pandey
I am a Ph.D. student at the University of Arkansas, advised by Dr. Khoa Luu. I conduct research in the Quantum AI Lab and the Computer Vision and Image Understanding Lab, where my work focuses on agents and multimodal reasoning for scientific discovery.
I previously received my B.S. in Computer Science and B.S. in Computer Engineering from the University of Arkansas.
I also love learning about history and playing sports like tennis, basketball, and pickleball.
Updates
- Sep. 2026: Agentic Multi-Turn Reasoning: A Fairness Approach accepted to NeurIPS 2026
- Sep. 2026: Presented OpenQlaw at the MonArk Supergroup Meeting.
- Aug. 2026: Started the PhD in Computer Science program at University of Arkansas as a Distinguished Doctoral Fellow.
- May 2026: Graduated from University of Arkansas with a B.S. in Computer Science and B.S. in Computer Engineering with minors in Mathematics and Data Analytics.
- Apr. 2026: Successfully defended Honors Thesis titled: "Autonomous Agentic Orchestration for Physics-Aware Scientific Discovery: An Integrative Multimodal Framework for 2D Material Characterization".
- Apr. 2026: Named a Senior of Significance for the Spring 2026 graduating class, recognizing 301 of 6,500+ graduates for leadership, achievement, and impact.
- Mar. 2026: Authored the OpenQlaw technical report and presented related work at the International Workshop on Automated 2D Materials and Quantum Devices.
- Mar. 2026: QuPAINT was accepted to CVPR Findings 2026.
- Feb. 2026: Awarded the Distinguished Doctoral Fellowship by the University of Arkansas.
- Jan. 2026: Accepted to the Ph.D. in Engineering (Computer Science) program at the University of Arkansas.
- Oct. 2025: CLIFF was accepted to the NeurIPS 2025 AI for Accelerated Materials Discovery Workshop.
- Sep. 2025: Featured by the University of Arkansas Honors College for research in quantum machine learning.
- Jul. 2025: Ranked 5th out of 67 teams in the Algonauts 2025 Vision-Brain Encoding Challenge.
- Jul. 2025: Awarded an Honors College Conference Travel Grant to present at a NeurIPS workshop.
- Jun. 2025: Featured by the University of Arkansas Honors College for research in neuroscience and nanomaterials.
- Apr. 2025: QMoE was accepted to the Quantum Computing & Reinforcement Learning Workshop at IEEE Quantum Week 2025.
- Feb. 2024: Joined the Computer Vision & Image Understanding Lab as an undergraduate research assistant.
Publications
Agentic Multi-Turn Reasoning: A Fairness Approach
Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill, Jackson Cothren, Marios Savvides, Khoa Luu
Fair Multi-Level Preference Optimization (Φ-MPO), which tackles long-horizon credit assignment and imbalanced training data for multi-turn, tool-using agents.
NeurIPS 2026
QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery
Xuan Bac Nguyen, Hoang-Quan Nguyen, Sankalp Pandey, Tim Faltermeier, Nicholas Borys, Hugh Churchill, Khoa Luu
A physics-aware instruction-tuning pipeline that improves multimodal reasoning for quantum material discovery.
CVPR Findings, 2026
CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
Sankalp Pandey, Xuan-Bac Nguyen, Nicholas Borys, Hugh Churchill, Khoa Luu
A continual learning strategy for incremental flake-feature identification with reduced catastrophic forgetting.
NeurIPS AI for Accelerated Materials Discovery Workshop, 2025
QMoE: A Quantum Mixture of Experts Framework for Scalable Quantum Neural Networks
Hoang-Quan Nguyen, Xuan-Bac Nguyen, Sankalp Pandey, Samee U. Khan, Ilya Safro, Khoa Luu
A quantum mixture-of-experts architecture that routes inputs to specialized experts for scalable quantum neural networks.
IEEE QCE QCRL Workshop, 2025