Trustworthy Post-Training & Agentic LLMs/VLMs · CS PhD Student @ UMBC NLP · Seeking Summer 2026 Research Internship

I am a CS PhD student at the University of Maryland, Baltimore County (UMBC) focusing on post-training optimization and system-level methods for LLMs and multimodal foundation models, especially agentic reasoning and controllable adaptation. Ongoing work spans

• Reasoning reliability and verification: retrieval-grounded structured inference and agentic retrieve-verify workflows for scientific claim and feasibility assessment, hallucination mitigation in multimodal QA (FilterRAG)

• Privacy-preserving and controllable model adaptation: federated fine-tuning of LLMs with Differential Privacy (FedMentor, FedMentalCare), targeted multimodal unlearning (Multimodal Unlearning Survey)

I am seeking Summer 2026 research internships in NLP and ML, focusing on post-training and agentic systems for trustworthy LLMs/VLMs, including alignment, robustness, privacy-preserving/federated learning, and multimodal unlearning.

Languages & Frameworks

Machine Learning / Deep Learning

Libraries & Tools

Distributed / Cloud / Systems