List your company
ResearchFormerly WizWand

Multimodal Dialogue Evaluation on LLaVA-Bench Wild (test)

97.7ScoreDense Connector
63.79672.59881.490.202May 22, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Dense ConnectorPT+IT=1.2M+1.5M, Res.=384 AnyRes, LLM=Yi-34B2024.0597.7
Dense ConnectorPT+IT=1.2M+1.5M, Res.=384 AnyRes, LLM=Vicuna-13B2024.0593.2
Dense ConnectorPT+IT=1.2M+1.5M, Res.=384, LLM=Vicuna-13B2024.0588.9
Dense ConnectorPT+IT=1.2M+1.5M, Res.=384 AnyRes, LLM=Vicuna-7B2024.0588.8
Mini-GeminiPT+IT=1.2M+1.5M, Res.=336+768, LLM=Vicuna-13B2024.0587.7
LLaVA-NeXTPT+IT=0.5M+0.7M, Res.=336 AnyRes, LLM=Vicuna-13B2024.0587.3
MM1PT+IT=3B+1.4M, Res.=1344, LLM=MM1-7B2024.0581.5
ShareGPT4VPT+IT=1.2M+0.7M, Res.=336, LLM=Vicuna-13B2024.0579.9
Dense ConnectorPT+IT=0.5M+0.6M, Res.=384, LLM=Yi-34B LORA2024.0575.1
Dense ConnectorPT+IT=0.5M+0.6M, Res.=384, LLM=Llama3-70B LORA2024.0574.5
Dense ConnectorPT+IT=0.5M+0.6M, Res.=384, LLM=Vicuna-13B2024.0573.6
VILAPT+IT=50M+1M, Res.=336, LLM=Llama-2-13B2024.0573
LLaVA-v1.5PT+IT=0.5M+0.6M, Res.=336, LLM=Vicuna-13B2024.0572.5
SPHINX-PlusPT+IT=16M, Res.=448, LLM=Llama2-13B2024.0571.7
CuMoPT+IT=0.5M+0.6M, Res.=336, LLM=Mistral-7B2024.0568.8
Dense ConnectorPT+IT=0.5M+0.6M, Res.=384, LLM=Llama3-8B2024.0568.8
TinyLLaVAPT+IT=0.5M+0.6M, Res.=384, LLM=Phi2-2.7B2024.0567.9
Dense ConnectorPT+IT=0.5M+0.6M, Res.=384, LLM=Vicuna-7B2024.0567.4
Dense ConnectorPT+IT=0.5M+0.6M, Res.=384, LLM=Phi2-2.7B2024.0565.1