paper-with-me

홈 › Papers

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

2024-12-06 · Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, Lixin Gu, Xuehui Wang, Qingyun Li, Yimin Ren, Zixuan Chen, Jiapeng Luo, Jiahao Wang, Tan Jiang, Bo wang, Conghui He, Botian Shi, Xingcheng Zhang, Han Lv, Yi Wang, Wenqi Shao, Pei Chu, Zhongying Tu, Tong He, Zhiyong Wu, Huipeng Deng, Jiaye Ge, Kai Chen, Kaipeng Zhang, LiMin Wang, Min Dou, Lewei Lu, Xizhou Zhu, Tong Lu, Dahua Lin, Yu Qiao, Jifeng Dai, Wenhai Wang

We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, real-world comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems. HuggingFace demo see https://huggingface.co/spaces/OpenGVLab/InternVL

📄 PDF Abstract BibTeX arXiv:2412.05271

Code (1)

opengvlab/internvl 공식 구현 pytorch

Tasks

document understandingHallucinationLanguage ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelVideo Question AnsweringVideo UnderstandingVisual GroundingVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction

2025-05-05 · Inclusion AI, Biao Gong, Cheng Zou, Dandan Zheng 외

We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, th…

Image Generationmultimodal interactionText to Image GenerationText-to-Image Generation

Ellipsoid-Based Decision Boundaries for Open Intent Classification

2025-11-13 · Yuetian Zou, Hanlei Zhang, Hua Xu, Songze Li 외 arxiv

Textual open intent classification is crucial for real-world dialogue systems, enabling robust detection of unknown user intents without prior knowledge and contributing to the robustness of the system. While adaptive de…

Open Intent DetectionIntent ClassificationContrastive LearningText Classification

Valley2: Exploring Multimodal Models with Scalable Vision-Language Design

2025-01-10 · Ziheng Wu, Zhenghao Chen, Ruipu Luo, Can Zhang 외

Recently, vision-language models have made remarkable progress, demonstrating outstanding capabilities in various tasks such as image captioning and video understanding. We introduce Valley2, a novel multimodal large lan…

Image CaptioningLanguage ModelingLanguage ModellingLarge Language Model+2

EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model

2023-12-05 · Guozhang Li, Xinpeng Ding, De Cheng, Jie Li 외

Early weakly supervised video grounding (WSVG) methods often struggle with incomplete boundary detection due to the absence of temporal boundary annotations. To bridge the gap between video-level and boundary-level annot…

Boundary DetectionLanguage ModelingLanguage ModellingLarge Language Model+2

Nomic Embed Vision: Expanding the Latent Space

2024-06-06 · Zach Nussbaum, Brandon Duderstadt, Andriy Mulyar

This technical report describes the training of nomic-embed-vision, a highly performant, open-code, open-weights image embedding model that shares the same latent space as nomic-embed-text. Together, nomic-embed-vision a…