paper-with-me

Papers

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

2024-10-17 · Rongyao Fang, Chengqi Duan, Kun Wang, Hao Li, Hao Tian, Xingyu Zeng, Rui Zhao, Jifeng Dai, Hongsheng Li, Xihui Liu

Recent advancements in multimodal foundation models have yielded significant progress in vision-language understanding. Initial attempts have also explored the potential of multimodal large language models (MLLMs) for visual content generation. However, existing works have insufficiently addressed the varying granularity demands of different image generation tasks within a unified MLLM paradigm - from the diversity required in text-to-image generation to the precise controllability needed in image manipulation. In this work, we propose PUMA, emPowering Unified MLLM with Multi-grAnular visual generation. PUMA unifies multi-granular visual features as both inputs and outputs of MLLMs, elegantly addressing the different granularity requirements of various image generation tasks within a unified MLLM framework. Following multimodal pretraining and task-specific instruction tuning, PUMA demonstrates proficiency in a wide range of multimodal tasks. This work represents a significant step towards a truly unified MLLM capable of adapting to the granularity demands of various visual tasks. The code and model will be released in https://github.com/rongyaofang/PUMA.

📄 PDF Abstract BibTeX arXiv:2410.13861

Code (1)

rongyaofang/puma 공식 구현 pytorch

Tasks

DiversityImage GenerationImage ManipulationText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning

2025-07-10 · Yibo Lyu, Rui Shao, Gongwei Chen, Yijie Zhu 외 arxiv

As multimedia content expands, the demand for unified multimodal retrieval (UMR) in real-world applications increases. Recent work leverages multimodal large language models (MLLMs) to tackle this task. However, their la…

Contrastive Learning

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

2024-08-16 · Wenwen Zhuang, Xin Huang, Xiantao Zhang, Jin Zeng

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids g…

MathMathematical ReasoningMultimodal Reasoning

GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images

2025-03-08 · Xiang Lan, Feng Wu, Kai He, Qinghao Zhao 외

While recent multimodal large language models (MLLMs) have advanced automated ECG interpretation, they still face two key limitations: (1) insufficient multimodal synergy between time series signals and visual ECG repres…

cross-modal alignmentDiagnosticTime Series

Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning

2023-09-16 · Sungyeon Kim, Donghyun Kim, Suha Kwak

A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of da…

Metric LearningTransfer Learning

Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM

2026-03-09 · Junyuan Mao, Qiankun Li, Linghao Meng, Zhicheng He 외 arxiv

Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides …