paper-with-me

홈 › Papers

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

2024-08-28 · Min Shi, Fuxiao Liu, Shihao Wang, Shijia Liao, Subhashree Radhakrishnan, Yilin Zhao, De-An Huang, Hongxu Yin, Karan Sapra, Yaser Yacoob, Humphrey Shi, Bryan Catanzaro, Andrew Tao, Jan Kautz, Zhiding Yu, Guilin Liu

The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves performance on resolution-sensitive tasks, such as optical character recognition and document analysis. A number of recent MLLMs achieve this goal using a mixture of vision encoders. Despite their success, there is a lack of systematic comparisons and detailed ablation studies addressing critical aspects, such as expert selection and the integration of multiple vision experts. This study provides an extensive exploration of the design space for MLLMs using a mixture of vision encoders and resolutions. Our findings reveal several underlying principles common to various existing strategies, leading to a streamlined yet effective design approach. We discover that simply concatenating visual tokens from a set of complementary vision encoders is as effective as more complex mixing architectures or strategies. We additionally introduce Pre-Alignment to bridge the gap between vision-focused encoders and language tokens, enhancing model coherence. The resulting family of MLLMs, Eagle, surpasses other leading open-source models on major MLLM benchmarks.

📄 PDF Abstract BibTeX arXiv:2408.15998

Code (2)

nvlabs/eagle 공식 구현 pytorch
bytedance/valley pytorch

Tasks

Optical Character Recognition

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing

2025-03-30 · Hongxiang Jiang, Jihao Yin, Qixiong Wang, Jiaqi Feng 외

Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges t…

AttributeDisentanglementObjectobject-detection+1

Veagle: Advancements in Multimodal Representation Learning

2024-01-18 · Rajat Chawla, Arkajit Datta, Tushar Verma, Adarsh Jha 외

Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual…

Image CaptioningLanguage ModellingQuestion AnsweringRepresentation Learning+3

EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models

2026-02-19 · Xiaomeng Peng, Xilang Huang, Seon Han Choi arxiv

Multimodal large language models (MLLMs) can enrich industrial anomaly detection with semantic descriptions and anomaly reasoning, but they still lag specialist anomaly detectors in binary detection accuracy. Existing ap…

Anomaly Detection

Embedding-Aligned Language Models

2024-05-24 · Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Lior Shani 외

We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an en…

Reinforcement Learning (RL)Text Generation

Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation

2025-09-26 · Ruoyu Chen, Xiaoqing Guo, Kangwei Liu, Siyuan Liang 외 arxiv

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual modalities remains po…