Models and data for ReflectiVA: Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering [CVPR 2025]
AImageLab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
18
aimagelab/ReT-OpenCLIP-ViT-G-14
Visual Document Retrieval
•
Updated
•
14
aimagelab/ReT-OpenCLIP-ViT-H-14
Visual Document Retrieval
•
Updated
•
19
aimagelab/ReflectiVA
Image-Text-to-Text
•
Updated
•
50
•
2
aimagelab/ReT-CLIP-ViT-L-14
Visual Document Retrieval
•
Updated
•
549
aimagelab/LLaVA_MORE-llama_3_1-8B-finetuning
Image-Text-to-Text
•
Updated
•
201
•
9
aimagelab/HySAC
Image-Text-to-Text
•
Updated
•
1
aimagelab/CoDE
Image Feature Extraction
•
Updated
•
1.18k
•
2
aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-finetuning
Image-Text-to-Text
•
Updated
•
4
•
2
aimagelab/LLaVA_MORE-llama_3_1-8B-S2-finetuning
Image-Text-to-Text
•
Updated
•
5
aimagelab/LLaVA_MORE-llama_3_1-8B-siglip-finetuning
Image-Text-to-Text
•
Updated
•
8
•
1