CoLVR-Models
Collection
3 items • Updated
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
CoLVR: Enhancing Exploratory Latent Visual Reasoning via Contrastive Optimization
Ziyang Ding, Linjian Meng, Yiming Wu, Yuhan Li, Yuhao Liu, Zhen Zhao†,
CoLVR (Contrastive Optimization for Latent Visual Reasoning) enables flexible and exploratory visual reasoning through latent contrastive training.
Overview
CoLVR-Jigsaw is our released model checkpoint for latent visual reasoning on the Jigsaw task. Training and evaluation code is available in our GitHub repository.
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support