Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for referring expression comprehension, and a language decoder for image captioning, etc. To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation, where our models learn to generate labels in text based on the visual and textual inputs. On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models. Moreover, our generative approach shows better generalization ability on questions that have rare answers. Also, we show that our framework allows multi-task learning in a single architecture with a single set of parameters, achieving similar performance to separately optimized single-task models. Our code is publicly available at: https://github.com/j-min/VL-T5
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）；Zhongguancun Academy（中关村学院）
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
Zhejiang University（浙江大学）；University of Electronic Science and Technology of China（电子科技大学）；Alibaba（阿里巴巴）；The Hong Kong University of Science and Technology（香港科技大学）；National University of Singapore（新加坡国立大学）
This paper presents Summary Workbench, a new tool for developing and evaluating text summarization models. New models and evaluation measures can be easily integrated as Docker-based plugins, allowing to examine the quality of their summaries against any input and to evaluate them using various evaluation measures. Visual analyses combining multiple measures provide insights into the models' strengths and weaknesses. The tool is hosted at \url{https://tldr.demo.webis.de} and also supports local deployment for private resources.
InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation
The Chinese University of Hong Kong（香港中文大学）；Fudan University（复旦大学）；Sensetime Research Institute（商汤研究院）；Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text description and align predicted words with object regions. To achieve this, models must generate desired text and box outputs together, and meanwhile indicate the alignments between words and boxes. In contrast to existing solutions that use multiple separate modules for different outputs, UniTAB represents both text and box outputs with a shared token sequence, and introduces a special <obj> token to naturally indica…
UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；School of Geographic Sciences, Hunan Normal University（湖南师范大学）；City University of Hong Kong（香港城市大学）
Unifying Adversarially Robust Model Experts in Vision-Language Models
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Center for Frontier AI Research, Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局前沿人工智能研究中心）
Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion Processes
School of Computer Science and Technology, University of Science and Technology of China（计算机科学与技术学院，中国科学技术大学）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）
Microsoft Research Asia（微软亚洲研究院）；Sun Yat-sen University（中山大学）；University of Science and Technology of China（中国科学技术大学）
We study the joint learning of image-to-text and text-to-image generations, which are naturally bi-directional tasks. Typical existing works design two separate task-specific models for each task, which impose expensive design efforts. In this work, we propose a unified image-and-text generative framework based on a single multimodal model to jointly study the bi-directional tasks. We adopt Transformer as our unified architecture for its strong performance and task-agnostic design. Specifically, we formulate both tasks as sequence generation tasks, where we represent images and text as unified…
Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University（上海数据科学 key laboratory，计算机科学学院，复旦大学）；School of Management, Fudan University（管理学院，复旦大学）；Tencent Weixin Group（腾讯微信集团）；IFM Lab, University of California, Davis（加州大学戴维斯分校IFM实验室）
Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem is only exacerbated by a lack of segmentation in transcripts of audio/video recordings. In this paper, we explore the role that section segmentation plays in extractive summarization of written and spoken documents. Our approach learns robust sentence representations by performing summarization and segmentation simultaneously, which is further enhanced by an…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Hong Kong University of Science and Technology（香港科技大学）；Sun Yat-sen University（中山大学）
Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts. Practically, there exist two typical types, \textit{i.e.}, the fusion-encoder type and the dual-encoder type, depending on whether a heavy fusion module is used. The former is superior at multi-modal tasks owing to the sufficient interaction between modalities; the latter is good at uni-modal and cross-modal tasks due to the single-modality encoding ability. To take advantage of these…
Unifying Structured Data as Graph for Data-to-Text Pre-Training
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）
Unifying Biomedical Vision-Language Expertise: Towards a Generalist Foundation Model via Multi-CLIP Knowledge Distillation
Department of Radiation Oncology, Winship Cancer Institute, Emory University School of Medicine（放射肿瘤科，Winship癌症研究所，埃默里大学医学院）；Department of Biomedical Engineering, College of Engineering, Georgia Institute of Technology（生物医学工程系，工程学院，佐治亚理工学院）；Department of Computer Science and Mathematics, Laney Graduate School, Emory University（计算机科学与数学系，兰尼研究生院，埃默里大学）；School of Electrical and Computer Engineering, College of Engineering, Georgia Institute of Technology（电气与计算机工程系，工程学院，佐治亚理工学院）
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, AAIS, Peking University（北京大学AAIS数据科学中心）；Ant Group（蚂蚁集团）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）
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 Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc., in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for d…
Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO
National University of Singapore（新加坡国立大学）；University of Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）；Wuhan University（武汉大学）
Due to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation. In this paper, we propose DU-VLG, a framework which unifies vision-and-language generation as sequence generation problems. DU-VLG is trained with novel dual pre-training tasks: multi-modal denoising autoencoder tasks and modality translation tasks. To bridge the gap between image understanding and generation, we further design a novel commitment loss. We compare pre-training objectives on image cap…
NAVER（NAVER公司）；Coupang（Coupang公司）；Seoul National University（首尔国立大学）
Contrastive learning is a form of distance learning that aims to learn invariant features from two related representations. In this paper, we explore the bold hypothesis that an image and its caption can be simply regarded as two different views of the underlying mutual information, and train a model to learn a unified vision-language representation space that encodes both modalities at once in a modality-agnostic manner. We first identify difficulties in learning a generic one-tower model for vision-language pretraining (VLP), and propose OneR as a simple yet effective framework for our goal.…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Microsoft Azure Cognitive Services Research（微软Azure认知服务研究院）；Microsoft Azure Visual Document Intelligence（微软Azure视觉文档智能部门）
We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation. With a novel Vision-Text-Layout Transformer, UDOP unifies pretraining and multi-domain downstream tasks into a prompt-based sequence generation scheme. UDOP is pretrained on both large-scale unlabeled document corpora using inno…
Microsoft（微软）；University of Washington（华盛顿大学）；Meta AI；UCLA（加州大学洛杉矶分校）
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning). GLIPv2 elegantly unifies localization pre-training and Vision-Language Pre-training (VLP) with three pre-training tasks: phrase grounding as a VL reformulation of the detection task, region-word contrastive learning as a novel region-word level contrastive learning task, and the masked language modeling. This unification not only simplifies the previous multi-stage VLP procedure but …
Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
The Ohio State University（俄亥俄州立大学）；Imperial College London（伦敦帝国学院）；The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Peking University（北京大学）
Even as pre-trained language encoders such as BERT are shared across many tasks, the output layers of question answering, text classification, and regression models are significantly different. Span decoders are frequently used for question answering, fixed-class, classification layers for text classification, and similarity-scoring layers for regression tasks, We show that this distinction is not necessary and that all three can be unified as span extraction. A unified, span-extraction approach leads to superior or comparable performance in supplementary supervised pre-trained, low-data, and …
TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Polytechnic University（香港理工大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Graduate School of AI, KAIST（韩国科学技术院人工智能研究生院）；MIT（麻省理工学院）；Asan Medical Center, University of Ulsan College of Medicine（蔚山大学医学院峨山医学中心）
EHR systems lack a unified code system forrepresenting medical concepts, which acts asa barrier for the deployment of deep learningmodels in large scale to multiple clinics and hos-pitals. To overcome this problem, we introduceDescription-based Embedding,DescEmb, a code-agnostic representation learning framework forEHR. DescEmb takes advantage of the flexibil-ity of neural language understanding models toembed clinical events using their textual descrip-tions rather than directly mapping each event toa dedicated embedding. DescEmb outperformedtraditional code-based embedding in extensiveexperi…
For text-level discourse analysis, there are various discourse schemes but relatively few labeled data, because discourse research is still immature and it is labor-intensive to annotate the inner logic of a text. In this paper, we attempt to unify multiple Chinese discourse corpora under different annotation schemes with discourse dependency framework by designing semi-automatic methods to convert them into dependency structures. We also implement several benchmark dependency parsers and research on how they can leverage the unified data to improve performance.
UC Santa Barbara（加州大学圣巴巴拉分校）；Meta；NEC Laboratories America（NEC美国实验室）
Generating a video given the first several static frames is challenging as it anticipates reasonable future frames with temporal coherence. Besides video prediction, the ability to rewind from the last frame or infilling between the head and tail is also crucial, but they have rarely been explored for video completion. Since there could be different outcomes from the hints of just a few frames, a system that can follow natural language to perform video completion may significantly improve controllability. Inspired by this, we introduce a novel task, text-guided video completion (TVC), which re…
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）
Recent works have shown explainability and robustness are two crucial ingredients of trustworthy and reliable text classification. However, previous works usually address one of two aspects: i) how to extract accurate rationales for explainability while being beneficial to prediction; ii) how to make the predictive model robust to different types of adversarial attacks. Intuitively, a model that produces helpful explanations should be more robust against adversarial attacks, because we cannot trust the model that outputs explanations but changes its prediction under small perturbations. To thi…
