paper-with-me

Papers

MLLM-DataEngine: An Iterative Refinement Approach for MLLM

2023-08-25 · Zhiyuan Zhao, Linke Ouyang, Bin Wang, Siyuan Huang, Pan Zhang, Xiaoyi Dong, Jiaqi Wang, Conghui He

Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost. In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results, then generate a proper incremental dataset for the next training iteration and enhance the model capability iteratively. Compared with previous data collection methods which are separate from the benchmarking, the data generated by MLLM-DataEngine shows better targeting, quality, and correctness. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data within each incremental dataset based on the benchmarking results. For quality, we resort to GPT-4 to generate high-quality data with each given data type. For correctness, prompt design is critical for the data generation results. Rather than previous hand-crafted prompt, we propose an Interactive Prompt Optimization strategy, which optimizes the prompt with the multi-round interaction between human and GPT, and improve the correctness of generated data greatly. Through extensive experiments, we find our MLLM-DataEngine could boost the MLLM capability in a targeted and automatic manner, with only a few human participation. We hope it could be a general solution for the following MLLMs building. The MLLM-DataEngine has been open-sourced and is now available at https://github.com/opendatalab/MLLM-DataEngine.

📄 PDF Abstract BibTeX arXiv:2308.13566

Code (1)

opendatalab/mllm-dataengine 공식 구현 pytorch

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Weight Decay 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement

2026-03-23 · Junrong Guo, Shancheng Fang, Yadong Qu, Hongtao Xie arxiv

Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generate…

Reinforcement Learning

Test-time Prompt Refinement for Text-to-Image Models

2025-07-22 · Mohammad Abdul Hafeez Khan, Yash Jain, Siddhartha Bhattacharyya, Vibhav Vineet arxiv

Text-to-image (T2I) generation models have made significant strides but still struggle with prompt sensitivity: even minor changes in prompt wording can yield inconsistent or inaccurate outputs. To address this challenge…

Image Generation

EXaMCaP: Subset Selection with Entropy Gain Maximization for Probing Capability Gains of Large Chart Understanding Training Sets

2026-02-04 · Jiapeng Liu, Liang Li, Bing Li, Peng Fu 외 arxiv

Recent works focus on synthesizing Chart Understanding (ChartU) training sets to inject advanced chart knowledge into Multimodal Large Language Models (MLLMs), where the sufficiency of the knowledge is typically verified…

Visual Reasoning and Multi-Agent Approach in Multimodal Large Language Models (MLLMs): Solving TSP and mTSP Combinatorial Challenges

2024-06-26 · Mohammed Elhenawy, Ahmad Abutahoun, Taqwa I. Alhadidi, Ahmed Jaber 외

Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the abi…

In-Context LearningTraveling Salesman ProblemVisual Reasoning

Grounding Everything in Tokens for Multimodal Large Language Models

2025-12-11 · Xiangxuan Ren, Zhongdao Wang, Liping Hou, Pin Tang 외 arxiv

Multimodal large language models (MLLMs) have made significant advancements in vision understanding and reasoning. However, the autoregressive Transformer architecture used by MLLMs requries tokenization on input images,…

Reinforcement Learning