中文
相关论文

相关论文: MobileVLM V2: Faster and Stronger Baseline for Vis…

200 篇论文

Large Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particularly for blind and low-vision (BLV) users who depend on…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Shruti Singh Baghel , Yash Pratap Singh Rathore , Sushovan Jena , Anurag Pradhan , Amit Shukla , Arnav Bhavsar , Pawan Goyal

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Han Wang , Yuxiang Nie , Yongjie Ye , Deng GuanYu , Yanjie Wang , Shuai Li , Haiyang Yu , Jinghui Lu , Can Huang

We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g.,…

Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and…

人工智能 · 计算机科学 2026-04-14 Sameera Horawalavithana , Lauren Phillips , Ian Stewart , Sai Munikoti , Karl Pazdernik

Vision Language Models (VLMs) have received significant attention in recent years in the robotics community. VLMs are shown to be able to perform complex visual reasoning and scene understanding tasks, which makes them regarded as a…

机器人学 · 计算机科学 2024-06-14 Siyuan Huang , Haonan Chang , Yuhan Liu , Yimeng Zhu , Hao Dong , Peng Gao , Abdeslam Boularias , Hongsheng Li

We introduce Shakti VLM, a family of vision-language models in the capacity of 1B and 4B parameters designed to address data efficiency challenges in multimodal learning. While recent VLMs achieve strong performance through extensive…

计算机视觉与模式识别 · 计算机科学 2025-10-20 Syed Abdul Gaffar Shakhadri , Kruthika KR , Kartik Basavaraj Angadi

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2…

计算与语言 · 计算机科学 2026-03-20 Ziyin Zhang , Zihan Liao , Hang Yu , Peng Di , Rui Wang

In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating basic visual dialog and reasoning, a performance gap persists…

计算机视觉与模式识别 · 计算机科学 2024-03-28 Yanwei Li , Yuechen Zhang , Chengyao Wang , Zhisheng Zhong , Yixin Chen , Ruihang Chu , Shaoteng Liu , Jiaya Jia

We introduce VisualPRM, an advanced multimodal Process Reward Model (PRM) with 8B parameters, which improves the reasoning abilities of existing Multimodal Large Language Models (MLLMs) across different model scales and families with…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Weiyun Wang , Zhangwei Gao , Lianjie Chen , Zhe Chen , Jinguo Zhu , Xiangyu Zhao , Yangzhou Liu , Yue Cao , Shenglong Ye , Xizhou Zhu , Lewei Lu , Haodong Duan , Yu Qiao , Jifeng Dai , Wenhai Wang

Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become inefficient at high…

Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing specialist medical VLMs requires substantial computational resources and carefully curated datasets,…

图像与视频处理 · 电气工程与系统科学 2026-03-31 Yuan Zhong , Ruinan Jin , Qi Dou , Xiaoxiao Li

Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As…

Visual grounding is an essential capability of Visual Language Models (VLMs) to understand the real physical world. Previous state-of-the-art grounding visual language models usually have large model sizes, making them heavy for deployment…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Guanqi Zhan , Changye Li , Zhijian Liu , Yao Lu , Yi Wu , Song Han , Ligeng Zhu

While recent large vision-language models (VLMs) have improved generalization in vision-language navigation (VLN), existing methods typically rely on end-to-end pipelines that map vision-language inputs directly to short-horizon discrete…

Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual…

机器学习 · 计算机科学 2025-07-15 Shivam Chandhok , Wan-Cyuan Fan , Vered Shwartz , Vineeth N Balasubramanian , Leonid Sigal

Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Siddharth Karamcheti , Suraj Nair , Ashwin Balakrishna , Percy Liang , Thomas Kollar , Dorsa Sadigh

The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Akash Ghosh , Arkadeep Acharya , Sriparna Saha , Vinija Jain , Aman Chadha

PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models. We combine the SigLIP-So400m vision encoder that was also used by PaliGemma with the whole range of Gemma 2 models,…

We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The model couples a SigLIP2 vision encoder with a Qwen3 language decoder and…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

计算与语言 · 计算机科学 2023-02-28 Weizhi Wang , Li Dong , Hao Cheng , Haoyu Song , Xiaodong Liu , Xifeng Yan , Jianfeng Gao , Furu Wei