Model and data for ReflectiVA: Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering [CVPR 2025]
Federico Cocchi
fede97
AI & ML interests
Multimodal LLM - Computer Vision
Recent Activity
updated
a model
1 day ago
aimagelab/LLaVA_MORE-gemma_2_2b-finetuning
published
a model
1 day ago
aimagelab/LLaVA_MORE-gemma_2_2b-finetuning
updated
a model
6 months ago
aimagelab/LLaVA_MORE-gemma_2_9b-dinov2-finetuning
Organizations
Dataset and models created inside the ELSA – European Lighthouse on Secure and Safe AI project on Multimedia use case.
LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1
Model and data for ReflectiVA: Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering [CVPR 2025]
The first generative model trained from scratch for Latin language
Dataset and models created inside the ELSA – European Lighthouse on Secure and Safe AI project on Multimedia use case.
https://arxiv.org/abs/2311.16254
LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1