List your company
ResearchFormerly WizWand

Harmful Meme Detection on HarM

83.82AccuracyMOMENTA
49.822458.648767.47576.3013Jul 9, 2025Aug 27, 2025Oct 15, 2025Dec 4, 2025Jan 22, 2026Mar 12, 2026May 1, 2026
Updated 5mo ago

Evaluation results

MethodLinks
MOMENTATraining/Evaluation Protocol=Training-based2025.0783.8282.8
MOMENTAProtocol=Supervised / Training-Based2026.0583.3282.8
Late FusionProtocol=Supervised / Training-Based2026.0573.2470.25
Late FusionTraining/Evaluation Protocol=Training-based2025.0773.2170.25
PrismAgentProtocol=Zero-Shot, Model Category=Agent-Based Methods (Open-Source), Backbone=LLaVA-1.6-34B2026.0571.1969.78
PrismAgentProtocol=Zero-Shot, Model Category=Agent-Based Methods (Open-Source), Backbone=LLaVA-1.5-13B2026.0570.6268.44
MINDBackbone=LLaVA-1.5-13B, Training/Evaluation Protocol=Training-free2025.0768.9365.19
MINDBackbone=LLaVA-1.5-13B, Setting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0768.9365.19
MINDProtocol=Zero-Shot, Model Category=Agent-Based Methods (Open-Source), Backbone=LLaVA-1.5-13B2026.0568.9365.19
GPT-4oSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0767.5160.29
LLaVA-1.6-34BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0767.5161.59
GPT-4oProtocol=Zero-Shot, Model Category=Closed-Source VLMs2026.0567.5160.29
LLaVA-1.6-34BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0567.5161.59
Gemini 1.5 FlashSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0766.164.18
InstructBLIP-13BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0764.9249.61
InstructBLIP-13BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0564.9249.61
Gemini-2.0-FlashProtocol=Zero-Shot, Model Category=Closed-Source VLMs2026.0564.6758.84
OpenFlamingo-9BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0763.4254.36
OpenFlamingo-9BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0563.4254.36
LLaVA-1.5-13BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0762.2850.45
LLaVA-1.5-13BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0562.2850.45
MiniGPT-v2-7BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0760.1252.39
MiniGPT-V-2BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0560.1252.39
LLaVA-1.5-7BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0759.2349.44
LLaVA-1.5-7BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0559.2349.44
InstructBLIP-7BProtocol=Zero-Shot, Model Category=Open-Source VLMs2026.0551.5350.99
InstructBLIP-7BSetting=Zero-shot, Prompt Strategy=Chain-of-Thought2025.0751.1350.99