Dominick Reilly
Scholar

Dominick Reilly

Google Scholar ID: YlFKOTkAAAAJ
UNC Charlotte
video understandingmultimodal learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
88
 
H-index
6
 
i10-index
3
 
Publications
12
 
Co-authors
0
 
Contact
Emaildreilly1@charlotte.eduCVOpen ↗GitHubOpen ↗
Publications
9 items
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
2026
Cited
0
World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
2026
Cited
0
TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living
2026
Cited
0
UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning
2026
Cited
0
UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models
2026
Cited
0
VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models
2025
Cited
0
SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living
2025
Cited
0
From My View to Yours: Ego-Augmented Learning in Large Vision Language Models for Understanding Exocentric Daily Living Activities
2025
Cited
0
Resume
Background
  • Fourth-year PhD student in Computer Science at the University of North Carolina at Charlotte
  • Advised by Dr. Srijan Das
  • Member of the Charlotte Machine Learning Lab (CharMLab)
  • Current research focus: multi-modal learning in Vision Language Models (VLMs) for video understanding and robotic control
  • Worked on ego-exo viewpoint transfer, cross-modal domain adaptation, and fine-grained action understanding
  • Interested in developing simple, generalizable, and scalable methods