OpenCodePapers

visual-question-answering-on-mmbench

Visual Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeGPT-3.5 scoreModelNameReleaseDate
Mixture-of-Subspaces in Low-Rank Adaptation✓ Link73.8LLaVA-InternLM2-ViT + MoSLoRA2024-06-16
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts✓ Link73.0CuMo-7B2024-05-09
Mixture-of-Subspaces in Low-Rank Adaptation✓ Link73.0LLaVA-LLaMA3-8B-ViT + MoSLoRA2024-06-16
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization✓ Link67.3Video-LaVIT2024-02-05
DreamLLM: Synergistic Multimodal Comprehension and Creation✓ Link49.9DreamLLM-7B2023-09-20