paper-with-me

Papers

From Text to Pixel: Advancing Long-Context Understanding in MLLMs

2024-05-23 · Yujie Lu, Xiujun Li, Tsu-Jui Fu, Miguel Eckstein, William Yang Wang

The rapid progress in Multimodal Large Language Models (MLLMs) has significantly advanced their ability to process and understand complex visual and textual information. However, the integration of multiple images and extensive textual contexts remains a challenge due to the inherent limitation of the models' capacity to handle long input sequences efficiently. In this paper, we introduce SEEKER, a multimodal large language model designed to tackle this issue. SEEKER aims to optimize the compact encoding of long text by compressing the text sequence into the visual pixel space via images, enabling the model to handle long text within a fixed token-length budget efficiently. Our empirical experiments on six long-context multimodal tasks demonstrate that SEEKER can leverage fewer image tokens to convey the same amount of textual information compared with the OCR-based approach, and is more efficient in understanding long-form multimodal input and generating long-form textual output, outperforming all existing proprietary and open-source MLLMs by large margins.

📄 PDF Abstract BibTeX arXiv:2405.14213

Code (1)

yujielu10/seeker 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language ModelLong-Context UnderstandingMultimodal Large Language ModelOptical Character Recognition (OCR)

Similar Papers 제목 키워드 기반

Towards robust long-context understanding of large language model via active recap learning

2026-01-20 · Chenyu Hui arxiv

In this paper, we propose active recap learning (ARL), a framework for enhancing large language model (LLM) in understanding long contexts. ARL enables models to revisit and summarize earlier content through targeted seq…

Long-Context Understanding

Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray

2025-02-07 · Yunhang Shen, Chaoyou Fu, Shaoqi Dong, Xiong Wang 외

Establishing the long-context capability of large vision-language models is crucial for video understanding, high-resolution image understanding, multi-modal agents and reasoning. We introduce Long-VITA, a simple yet eff…

4kGeneral KnowledgeGPULanguage Modeling+3

AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation

2021-01-26 · ICCV 2021 10 · Yaxiong Wang, Yunchao Wei, Yujiao Wu, Xueming Qian 외

Superpixel segmentation has seen significant progress benefiting from the deep convolutional networks. The typical approach entails initial division of the image into grids, followed by a learning process that assigns ea…

Segmentation

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

2026-05-13 · Zhaowei Wang, Lishu Luo, Haodong Duan, Weiwei Liu 외 arxiv

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in age…

Information Retrieval

CP-LLM: Context and Pixel Aware Large Language Model for Video Quality Assessment

2025-05-21 · Wen Wen, Yaohong Wu, Yue Sheng, Neil Birkbeck 외

Video quality assessment (VQA) is a challenging research topic with broad applications. Effective VQA necessitates sensitivity to pixel-level distortions and a comprehensive understanding of video context to accurately d…

Language ModelingLanguage ModellingLarge Language ModelSensitivity+2