English
Related papers

Related papers: Cross-Modal Fine-Tuning: Align then Refine

200 papers

Recently, Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Wayner Barrios , Andrés Villa , Juan León Alcázar , SouYoung Jin , Bernard Ghanem

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Qinwu Xu , Yifan Jiang , Haoyu Ren

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Peng Wang , An Yang , Rui Men , Junyang Lin , Shuai Bai , Zhikang Li , Jianxin Ma , Chang Zhou , Jingren Zhou , Hongxia Yang

Results in interpretability suggest that large vision and language models learn implicit linear encodings when models are biased by in-context prompting. However, the existence of similar linear representations in more general adaptation…

Machine Learning · Computer Science 2025-12-18 Darrin O' Brien , Dhikshith Gajulapalli , Eric Xia

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Jiaxiang Liu , Yuan Wang , Jiawei Du , Joey Tianyi Zhou , Mingkun Xu , Zuozhu Liu

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

There are a wide range of applications that involve multi-modal data, such as cross-modal retrieval, visual question-answering, and image captioning. Such applications are primarily dependent on aligned distributions of the different…

Machine Learning · Computer Science 2020-05-26 Vishaal Udandarao , Abhishek Maiti , Deepak Srivatsav , Suryatej Reddy Vyalla , Yifang Yin , Rajiv Ratn Shah

Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning, yet limited annotated datasets restrict medical-specific model development. While vision-language models (VLMs) like CLIP offer strong…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Zelin Peng , Yichen Zhao , Yu Huang , Piao Yang , Feilong Tang , Zhengqin Xu , Xiaokang Yang , Wei Shen

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Machine Learning · Computer Science 2025-11-11 Evelyn Chee , Wynne Hsu , Mong Li Lee

Although the advancements of pre-trained Large Language Models have significantly accelerated recent progress in NLP, their ever-increasing size poses significant challenges for conventional fine-tuning, especially in memory-intensive…

Computation and Language · Computer Science 2024-04-02 Chenxi Whitehouse , Fantine Huot , Jasmijn Bastings , Mostafa Dehghani , Chu-Cheng Lin , Mirella Lapata

Multimodal large language models (MLLMs) hold promise for integrating diverse data modalities, but current medical adaptations such as LLaVA-Med often fail to fully exploit the synergy between color fundus photography (CFP) and optical…

We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner…

Machine Learning · Computer Science 2020-01-10 Eunbyung Park , Junier B. Oliva

Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate…

Computation and Language · Computer Science 2026-01-13 Wenhong Zhu , Weinan Zhang , Rui Wang

Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Ziqi Jiang , Yanghao Wang , Long Chen

Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Xingyi He , Hao Yu , Sida Peng , Dongli Tan , Zehong Shen , Hujun Bao , Xiaowei Zhou

The natural world is abundant with concepts expressed via visual, acoustic, tactile, and linguistic modalities. Much of the existing progress in multimodal learning, however, focuses primarily on problems where the same set of modalities…

Machine Learning · Computer Science 2020-12-08 Paul Pu Liang , Peter Wu , Liu Ziyin , Louis-Philippe Morency , Ruslan Salakhutdinov

Prompt Tuning has emerged as a prominent research paradigm for adapting vision-language models to various downstream tasks. However, recent research indicates that prompt tuning methods often lead to overfitting due to limited training…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Jingchen Sun , Rohan Sharma , Vishnu Suresh Lokhande , Changyou Chen

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Souhail Bakkali , Zuheng Ming , Mickael Coustaty , Marçal Rusiñol , Oriol Ramos Terrades

With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Tengjun Huang