[BMVC 2025] Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization - Models and Datasets
AI & ML interests
None defined yet.
Recent Activity
models 40
aimagelab/jarvis-qwen2-7B-clip
665k • Updated
• 27
aimagelab/LLaVA_MORE-gemma_2_2b-finetuning
Image-Text-to-Text • 3B • Updated
• 6
aimagelab/CHAIR-DPO_LLaVA-MORE-8B
8B • Updated
aimagelab/CHAIR-DPO_LLaVA-1.5-7B
7B • Updated
aimagelab/DICE_coherence_Idefics
Updated
aimagelab/DICE_differencedet_Idefics
Updated
aimagelab/ReT2-M2KR-ColBERT-SigLIP2-ViT-L
Visual Document Retrieval • 0.4B • Updated
• 30
aimagelab/ReT2-MBEIR-SigLIP2-ViT-L
Visual Document Retrieval • 0.9B • Updated
• 5 • 1
aimagelab/ReT2-MBEIR-CLIP-ViT-L
Visual Document Retrieval • 0.4B • Updated
aimagelab/ReT2-M2KR-ColBERT-CLIP-ViT-L
Visual Document Retrieval • 0.4B • Updated
• 1
datasets 6
aimagelab/ReT-M2KR
Preview
• Updated
• 705 • 2
aimagelab/CHAIR-DPO_preference_datasets
Viewer
• Updated
• 1.39M • 13
aimagelab/HeisenVec
Viewer
• Updated
• 935k • 497 • 1
aimagelab/RAID
Preview
• Updated
• 1.4k • 2
aimagelab/ReflectiVA-Data
Preview
• Updated
• 51
aimagelab/ViSU-Text
Viewer
• Updated
• 169k • 21 • 10