List your company

Multi-image Reasoning on DEMON

38.94AccuracyBrote-IM-XXL
23.932827.828931.72535.6211Feb 19, 2024

Evaluation results

MethodLinks
Brote-IM-XXLLLM Backbone=FlanT5, #Param LLM=11B2024.0238.94
Brote-IM-XXL (ours)#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.0238.94
Brote-EX-XXLLLM Backbone=FlanT5, #Param LLM=11B2024.0238.7
Brote-EX-XXL (ours)#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.0238.7
MMICL-XLLLM Backbone=FlanT5, #Param LLM=3B2024.0238.14
MMICL-XL#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.0238.14
Brote-IM-XLLLM Backbone=FlanT5, #Param LLM=3B2024.0237.34
Brote-IM-XL (ours)#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.0237.34
Brote-EX-XLLLM Backbone=FlanT5, #Param LLM=3B2024.0237.33
Brote-EX-XL (ours)#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.0237.33
VPG-C-LLAMA2LLM Backbone=LLAMA, #Param LLM=7B2024.0237.22
VPG-C-LLaMA2#Param LLM=7B, Task Setting=Multi-image / Video Tasks2024.0237.22
VPG-C-VicunaLLM Backbone=Vicuna, #Param LLM=13B2024.0236.37
MMICL-XXLLLM Backbone=FlanT5, #Param LLM=11B2024.0236.3
MMICL-XXL#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.0236.3
InstructBLIP-XXLLLM Backbone=FlanT5, #Param LLM=11B2024.0233
InstructBLIP-XXL#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.0233
InstructBLIP-XLLLM Backbone=FlanT5, #Param LLM=3B2024.0232.59
InstructBLIP-XL#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.0232.59
OtterLLM Backbone=MPT, #Param LLM=7B2024.0224.51
Otter#Param LLM=7B, Task Setting=Multi-image / Video Tasks2024.0224.51