2 papers
cs.CV2026
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
Pranav Mantini, Shishir K. Shah
We address the challenge of knowledge composition in Vision-Language Models (VLMs), where accumulating expertise across multiple domains or tasks typically leads to catastrophic fo…
cs.CV2026
BiCLIP: Domain Canonicalization via Structured Geometric Transformation
Pranav Mantini, Shishir K. Shah
Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challen…