RESEARCH PAPERYear 2024

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

Siddharth Karamcheti; Suraj Nair; Ashwin Balakrishna; Percy Liang; Thomas Kollar; Dorsa Sadigh

Classification

View four quadrants
Major category
Components of WAMs
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Explicit in survey

Category review. Prismatic provides reusable VLM architectures joining pretrained visual features through a projection into language generation. Its DINOv2/SigLIP fusion and resulting PRISM family supply visual-language representations explicitly reused by the manuscript discussion. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX