List your company

Visual Question Answering on VQAv2 18

82.4AccuracyMipha-3B+ (Ours)
49.6458.14566.6575.155Jul 5, 2024

Evaluation results

MethodLinks
Mipha-3B+ (Ours)LM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0782.4
Mipha-3BLM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0781.3
MoE-LLaVA-3.6BLM=Phi-2 (2.7B), Res.=384, PT=558k, IT=1.59M2024.0779.9
TinyLLaVALM=Phi-2 (2.7B), Res.=384, PT=1.2M, IT=665k2024.0779.9
LLaVA-1.5+ (Ours)LM=Vicuna(7B), Res.=336, PT=558K, IT=665K2024.0779.8
Bunny-3BLM=Phi-2 (2.7B), Res.=384, PT=2M, IT=695K2024.0779.8
Imp-v1LM=Phi-2 (2.7B), Res.=384, PT=558K, IT=665K2024.0779.5
mPLUG-Owl2LM=LLAMA (7B), Res.=448, PT=400M, IT=1.23M2024.0779.4
LAF-7BLM=Vicuna (7B), Res.=336, PT=558K, IT=665K2024.0779
Qwen-VLLM=Qwen (7B), Res.=448, PT=1.4B, IT=50M2024.0778.8
LLaVA-1.5LM=Vicuna (7B), Res.=336, PT=558K, IT=665K2024.0778.5
Qwen-VL-ChatLM=Qwen (7B), Res.=448, PT=1.4B, IT=50M2024.0778.2
ShikraLM=Vicuna (13B), Res.=224, PT=600K, IT=5.5M2024.0777.4
IDEFICS-80BLM=LLaMA (65B), Res.=224, PT=353M, IT=1M2024.0760
IDEFICS-9BLM=LLaMA (7B), Res.=224, PT=353M, IT=1M2024.0750.9