List your company

Visual Question Answering on VQA v1

83.2AccuracyGoM (Object Num IDs + Relation labels)
45.55255.32665.174.874Sep 28, 2022Apr 24, 2023Nov 19, 2023Jun 14, 2024Jan 9, 2025Aug 5, 2025Mar 2, 2026

Evaluation results

MethodLinks
GoM (Object Num IDs + Relation labels)MLM=LlamaV-o1-11B2026.0383.2
GoM (Object Text IDs + Relation labels)MLM=Qwen-2.5-VL-7B2026.0382.5
GoM (Object Num IDs + Relation labels)MLM=Qwen-2.5-VL-7B2026.0381.1
GoM (Object Text IDs + Relation labels)MLM=LlamaV-o1-11B2026.0379.8
GoM (Object Num IDs)MLM=Qwen-2.5-VL-7B2026.0378.1
GoM (Object Text IDs)MLM=Qwen-2.5-VL-7B2026.0377.9
GoM (Object Num IDs)MLM=LlamaV-o1-11B2026.0377.9
Raw imageMLM=Qwen-2.5-VL-7B2026.0377.7
GoM (Object Text IDs)MLM=LlamaV-o1-11B2026.0376
Raw imageMLM=LlamaV-o1-11B2026.0375.3
GoM (Object Text IDs + Relation labels)MLM=Gemma-3-4B2026.0374.2
SoMMLM=LlamaV-o1-11B2026.0372.8
Segmented objectsMLM=LlamaV-o1-11B2026.0372.6
GoM (Object Num IDs)MLM=Gemma-3-4B2026.0371.5
GoM (Object Num IDs + Relation labels)MLM=Gemma-3-4B2026.0371.2
SoMMLM=Qwen-2.5-VL-7B2026.0365.4
GoM (Object Text IDs)MLM=Gemma-3-4B2026.0365.2
Segmented objectsMLM=Qwen-2.5-VL-7B2026.0365.2
Raw imageMLM=Gemma-3-4B2026.0364.3
SoMMLM=Gemma-3-4B2026.0363.8
Segmented objectsMLM=Gemma-3-4B2026.0363.7
TVLTInput Modality=Visual, Audio, Pretrain Datasets=YTT-S2022.0958.9
TVLTInput Modality=Visual, Audio, Pretrain Datasets=HT100M2022.0958.6
TextModInput Modality=Visual, Text2022.0956.7
SpeechModInput Modality=Visual, Audio2022.0947