REVIEW 5 cited by
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human-AI interaction applications. Therefore, we introduce MMDU, a comprehensive benchmark, and MMDU-45k, a large-scale instruction tuning dataset, designed to evaluate and improve LVLMs' abilities in multi-turn and multi-image conversations. We employ the clustering algorithm to ffnd the relevant images and textual descriptions from the open-source Wikipedia and construct the question-answer pairs by human annotators with the assistance of the GPT-4o model. MMDU has a maximum of 18k image+text tokens, 20 images, and 27 turns, which is at least 5x longer than previous benchmarks and poses challenges to current LVLMs. Our in-depth analysis of 15 representative LVLMs using MMDU reveals that open-source LVLMs lag behind closed-source counterparts due to limited conversational instruction tuning data. We demonstrate that ffne-tuning open-source LVLMs on MMDU-45k signiffcantly address this gap, generating longer and more accurate conversations, and improving scores on MMDU and existing benchmarks (MMStar: +1.1%, MathVista: +1.5%, ChartQA:+1.2%). Our contributions pave the way for bridging the gap between current LVLM models and real-world application demands. This project is available at https://github.com/Liuziyu77/MMDU.
Forward citations
Cited by 5 Pith papers
-
EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards
A self-evolving multimodal model using continuous self-consistency rewards improves math reasoning by about 2–3% using only raw images, without labels or external reward models.
-
CoMemo: LVLMs Need Image Context with Image Memory
CoMemo adds a cross-attention image-memory path and thumbnail-anchored position encoding to reduce visual neglect in long-context and multi-image LVLM tasks.
-
Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
Context-to-Cue Direct Preference Optimization (CcDPO) reduces multi-image hallucinations in 7B multimodal LLMs by training on perturbed full-sequence captions and region-focused visual prompts, improving average multi...
-
Medical Large Vision Language Models with Multi-Image Visual Ability
Fine-tuning medical vision-language models on the Med-MIM multi-image instruction dataset improves their scores on the authors' multi-image benchmarks, but the held-in benchmark is drawn from the same data used for training.
-
Docopilot: Improving Multimodal Models for Document-Level Understanding
A new academic-paper dataset and a retrieval-free fine-tuned InternVL2 model improve multi-page document QA accuracy and latency on several benchmarks.
Discussion (0). Sign in to comment.