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
new activity about 24 hours ago
aimagelab/RAID:Add PGD / APGD / CWA adversarial splits (eps 8/16/32) new activity about 24 hours ago
aimagelab/RAID_ckpt:Add Effort, AIDE, D3, OmniAID, DDA checkpoints updated a model 9 months ago
aimagelab/LLaVA_MORE-gemma_2_2b-finetuningOrganizations
models 0
None public yet
datasets 5
fede97/external_test_set_v1
Viewer • Updated • 340 • 41
fede97/external_data_test_example_v3
Updated • 4
fede97/external_data_test_example
Viewer • Updated • 410 • 56
fede97/external_data_test_example_v2
Viewer • Updated • 410 • 69
fede97/dpo_demo
Viewer • Updated • 148k • 9