Research
My research centers on developing robust, reliable, and scalable AI systems that address real-world challenges. I focus on creating solutions that not only advance the theoretical foundations of machine learning but also translate into practical applications with measurable impact.
I have been fortunate to collaborate with exceptional researchers and scientists from leading institutions including Microsoft Research, Google DeepMind, Amazon Science, and various national laboratories. Their expertise and guidance have been instrumental in shaping this work, and I am deeply grateful for these partnerships.
Much of this research has found its way into production systems and solutions deployed at scale, demonstrating the practical value of advancing both theoretical understanding and applied methodology in building trustworthy AI systems.
Selected Publications
All Publications
View all →Context Determines Optimal Architecture in Materials Segmentation
In ICLR 2026 AI4MAT Workshop
Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
arXiv preprint, 2026
Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
arXiv preprint, 2026
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
arXiv preprint, 2026
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
arXiv preprint, 2026
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
arXiv preprint, 2026
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
arXiv preprint, 2026
A Survey on Agent Skills for LLMs: A Lifecycle Perspective from Construction to Ecosystems
arXiv preprint, 2026
Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks
In NeurIPS 2025
Forte: Finding Outliers with Representation Typicality Estimation
In The Thirteenth International Conference on Learning Representations, 2025
LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision
In IEEE BigData, 2025
Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM
In HiPC, 2025
Proof of thought: Neurosymbolic program synthesis allows robust and interpretable reasoning
In The First Workshop on System-2 Reasoning at Scale, NeurIPS'24 Sys2-Reasoning, 2024
Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks
In 4th International Conference on Pattern Recognition and Artificial Intelligence, 2024
Enhancing Scientific Image Classification through Multimodal Learning: Insights from Chest X-Ray and Atomic Force Microscopy Datasets
In 2023 IEEE International Conference on Big Data (BigData), pp. 2211-2220, 2023