English
Related papers

Related papers: Visual Compositional Tuning

200 papers

CLIP and large multimodal models (LMMs) have better accuracy on examples involving concepts that are highly represented in the training data. However, the role of concept combinations in the training data on compositional generalization is…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Helen Qu , Sang Michael Xie

In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph into an unified autoregressive model capable of generating…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Shengbang Tong , David Fan , Jiachen Zhu , Yunyang Xiong , Xinlei Chen , Koustuv Sinha , Michael Rabbat , Yann LeCun , Saining Xie , Zhuang Liu

The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Jiawang Bai , Li Yuan , Shu-Tao Xia , Shuicheng Yan , Zhifeng Li , Wei Liu

Automated radiology report summarization aims to distill verbose findings into concise clinical impressions, but existing multimodal models often struggle with visual noise and fail to meaningfully improve over strong text-only baselines in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Mst. Fahmida Sultana Naznin , Adnan Ibney Faruq , Mushfiqur Rahman , Niloy Kumar Mondal , Md. Mehedi Hasan Shawon , Md Rakibul Hasan

Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (e.g., attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Kwanyong Park , Kuniaki Saito , Donghyun Kim

In recent years, data selection has emerged as a core issue for large-scale visual-language model pretraining, especially on noisy web-curated datasets. One widely adopted strategy assigns quality scores such as CLIP similarity for each…

Machine Learning · Computer Science 2024-02-06 Yiping Wang , Yifang Chen , Wendan Yan , Kevin Jamieson , Simon Shaolei Du

Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…

Machine Learning · Computer Science 2025-06-05 Gianluigi Silvestri , Luca Ambrogioni , Chieh-Hsin Lai , Yuhta Takida , Yuki Mitsufuji

The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Menglin Jia , Luming Tang , Bor-Chun Chen , Claire Cardie , Serge Belongie , Bharath Hariharan , Ser-Nam Lim

Medical imaging provides essential visual insights for diagnosis, and multimodal large language models (MLLMs) are increasingly utilized for its analysis due to their strong generalization capabilities; however, the underlying factors…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Zhenyang Cai , Junying Chen , Rongsheng Wang , Weihong Wang , Yonglin Deng , Dingjie Song , Yize Chen , Zixu Zhang , Benyou Wang

Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to…

Computation and Language · Computer Science 2025-12-16 Dairu Liu , Ziyue Wang , Minyuan Ruan , Fuwen Luo , Chi Chen , Peng Li , Yang Liu

While Large Language Models (LLMs) acquire vast knowledge during pre-training, they often lack domain-specific, new, or niche information. Continual pre-training (CPT) attempts to address this gap but suffers from catastrophic forgetting…

Computation and Language · Computer Science 2025-04-09 Oded Ovadia , Meni Brief , Rachel Lemberg , Eitam Sheetrit

Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However,…

Computation and Language · Computer Science 2025-05-20 Chi Zhang , Huaping Zhong , Hongtao Li , Chengliang Chai , Jiawei Hong , Yuhao Deng , Jiacheng Wang , Tian Tan , Yizhou Yan , Jiantao Qiu , Ye Yuan , Guoren Wang , Conghui He , Lei Cao

Due to the severe lack of labeled data, existing methods of medical visual question answering usually rely on transfer learning to obtain effective image feature representation and use cross-modal fusion of visual and linguistic features to…

Multimedia · Computer Science 2021-05-04 Haifan Gong , Guanqi Chen , Sishuo Liu , Yizhou Yu , Guanbin Li

Despite vision-language models' (VLMs) remarkable capabilities as versatile visual assistants, two substantial challenges persist within the existing VLM frameworks: (1) lacking task diversity in pretraining and visual instruction tuning,…

Computation and Language · Computer Science 2024-02-20 Zhiyang Xu , Chao Feng , Rulin Shao , Trevor Ashby , Ying Shen , Di Jin , Yu Cheng , Qifan Wang , Lifu Huang

While pre-trained multimodal representations (e.g., CLIP) have shown impressive capabilities, they exhibit significant compositional vulnerabilities leading to counterintuitive judgments. We introduce Multimodal Adversarial Compositionality…

Computation and Language · Computer Science 2025-05-30 Jaewoo Ahn , Heeseung Yun , Dayoon Ko , Gunhee Kim

Multimodal learning has shown promise in medical imaging, combining complementary modalities like images and text. Vision-language models (VLMs) capture rich diagnostic cues but often require large paired datasets and prompt- or text-based…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Banafsheh Karimian , Giulia Avanzato , Soufian Belharbi , Alexis Guichemerre , Luke McCaffrey , Mohammadhadi Shateri , Eric Granger

Data quality and diversity are key to the construction of effective instruction-tuning datasets. % With the increasing availability of open-source instruction-tuning datasets, it is advantageous to automatically select high-quality and…

Computation and Language · Computer Science 2025-04-21 Yicheng Chen , Yining Li , Kai Hu , Zerun Ma , Haochen Ye , Kai Chen

The visual world around us constantly evolves, from real-time news and social media trends to global infrastructure changes visible through satellite imagery and augmented reality enhancements. However, Multimodal Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Mingyang Fu , Yuyang Peng , Dongping Chen , Zetong Zhou , Benlin Liu , Yao Wan , Zhou Zhao , Philip S. Yu , Ranjay Krishna

Visual instruction tuning is crucial for improving vision-language large models (VLLMs). However, many samples can be solved via linguistic patterns or common-sense shortcuts, without genuine cross-modal reasoning, limiting the…

Artificial Intelligence · Computer Science 2026-03-11 Peng Sun , Huawen Shen , Yi Ban , Tianfan Fu , Yanbo Wang , Yuqiang Li

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Wenshuo Peng , Kaipeng Zhang , Yue Yang , Hao Zhang , Yu Qiao