Federico Cocchi

fede97's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a model 12 days ago

aimagelab/CoDE

Image Feature Extraction • Updated 12 days ago • 1.07k • 2

authored a paper 27 days ago

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

Paper • 2411.16863 • Published 29 days ago

updated a model 27 days ago

aimagelab/ReflectiVA

Image-Text-to-Text • Updated 27 days ago • 12 • 1

updated a collection 29 days ago

ELSA EU Project

Collection

Dataset and models created inside the ELSA – European Lighthouse on Secure and Safe AI project on Multimedia use case. • 4 items • Updated 29 days ago

updated a collection 4 months ago

LLaVA-MORE

Collection

LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1 • 2 items • Updated Aug 31

New activity in aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-finetuning 4 months ago

checkpoint you are trying to load has model type `llava_llama` but Transformers does not recognize this architecture

2

#1 opened 4 months ago by

joris-sense

updated a model 4 months ago

aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-finetuning

Image-Text-to-Text • Updated Aug 16 • 13 • 2

updated a collection 4 months ago

LLaVA-MORE

Collection

LLaVA-MORE: Enhancing Visual Instruction Tuning with LLaMA 3.1 • 8 items • Updated Aug 16 • 1

updated 3 models 4 months ago

aimagelab/LLaVA_MORE-llama_3_1-8B-S2-finetuning

Image-Text-to-Text • Updated Aug 16 • 9

aimagelab/LLaVA_MORE-llama_3_1-8B-siglip-finetuning

Image-Text-to-Text • Updated Aug 16 • 17 • 1

aimagelab/LLaVA_MORE-llama_3_1-8B-S2-siglip-pretrain

Image-Text-to-Text • Updated Aug 16 • 8