MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
Scaling up visual and vision-language representa- tion learning with noisy text supervision
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
AuralSAM2 fuses audio-visual features via a pyramid-based AuralFuser module and audio-guided contrastive loss to improve promptable segmentation accuracy in SAM2 with minimal efficiency impact.
LVLM-ReID guides LVLMs to produce refined semantic tokens as pedestrian identity features for ReID, achieving competitive benchmark results without additional image-text data.
A new 1.2M-caption dataset generated via GPT-4V improves LMMs on MME and MMBench by 222.8/22.0/22.3 and 2.7/1.3/1.5 points respectively when used for supervised fine-tuning.
LPT reduces overfitting during prompt tuning of VLMs by CLIP-based foreground filtering, a structural preservation constraint aligning features to frozen CLIP, and a hierarchical logit constraint at the output, improving generalization on base-to-novel, cross-dataset, and domain-generalization tasks
citing papers explorer
-
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
-
AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
AuralSAM2 fuses audio-visual features via a pyramid-based AuralFuser module and audio-guided contrastive loss to improve promptable segmentation accuracy in SAM2 with minimal efficiency impact.
-
When Large Vision-Language Models Meet Person Re-Identification
LVLM-ReID guides LVLMs to produce refined semantic tokens as pedestrian identity features for ReID, achieving competitive benchmark results without additional image-text data.
-
ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
A new 1.2M-caption dataset generated via GPT-4V improves LMMs on MME and MMBench by 222.8/22.0/22.3 and 2.7/1.3/1.5 points respectively when used for supervised fine-tuning.
-
LPT: Less-overfitting Prompt Tuning for Vision-Language Model
LPT reduces overfitting during prompt tuning of VLMs by CLIP-based foreground filtering, a structural preservation constraint aligning features to frozen CLIP, and a hierarchical logit constraint at the output, improving generalization on base-to-novel, cross-dataset, and domain-generalization tasks