Bang Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bang Yang has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Yuexian Zou
Peking University
9 shared publications - Fenglin Liu
University of Oxford
7 shared publications Yuexian Zou
Peking University
7 shared publications- Chris Kelly
Seeking AI Seeking AI Seeking AI Harvard University Stanford University Peking University University of Washington Seattle Peking University
4 shared publications - Cindy Yang
Seeking AI Seeking AI Seeking AI Harvard University Stanford University Peking University University of Washington Seattle Peking University
4 shared publications Deshun Yang
4 shared publications
Latest Publications
- Open Access
Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly localized: a small subset of low-confidence tokens disproportionately contributes to reasoning errors and unnecessary output expansion. Motivated by this observation, we propose Thinking by Subtraction, a confidence-driven contrastive decoding approach that improves reasoning reliability through targeted token-level intervention. Our method, Confidence-Driven Contrastive Decoding, detects low-confidence tokens during decoding and intervenes selectively at these positions. It constructs a contrastive reference by replacing high-confidence tokens with minimal placeholders, and refines predictions by subtracting this reference distribution at low-confidence locations. Experiments show that CCD significantly improves accuracy across mathematical reasoning benchmarks while substantially reducing output length, with minimal KV-cache overhead. As a training-free method, CCD enhances reasoning reliability through targeted low-confidence intervention without computational redundancy. Our code will be made available at: https://github.com/bolo-web/CCD.
Open AccessThinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly localized: a small subset of low-confidence tokens disproportionately contributes to reasoning errors and unnecessary output expansion. Motivated by this observation, we propose Thinking by Subtraction, a confidence-driven contrastive decoding approach that improves reasoning reliability through targeted token-level intervention. Our method, Confidence-Driven Contrastive Decoding, detects low-confidence tokens during decoding and intervenes selectively at these positions. It constructs a contrastive reference by replacing high-confidence tokens with minimal placeholders, and refines predictions by subtracting this reference distribution at low-confidence locations. Experiments show that CCD significantly improves accuracy across mathematical reasoning benchmarks while substantially reducing output length, with minimal KV-cache overhead. As a training-free method, CCD enhances reasoning reliability through targeted low-confidence intervention without computational redundancy. Our code will be made available at: https://github.com/bolo-web/CCD.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3332-3343
Aligning, Autoencoding and Prompting Large Language Models for Novel Disease Reporting
Given radiology images, automatic radiology report generation aims to produce informative text that reports diseases. It can benefit current clinical practice in diagnostic radiology. Existing methods typically rely on large-scale medical datasets annotated by clinicians to train desirable models. However, for novel diseases, sufficient training data are typically not available. We propose a prompt-based deep learning framework, i.e., PromptLLM, to align, autoencode, and prompt the (large) language model to generate reports for novel diseases accurately and efficiently. Our method includes three major steps: (1) aligning visual images and textual reports to learn general knowledge across modalities from diseases where labeled data are sufficient, (2) autoencoding the LLM using unlabeled data of novel diseases to learn the specific knowledge and writing styles of the novel disease, and (3) prompting the LLM with learned knowledge and writing styles to report the novel diseases contained in the radiology images. Through the above three steps, with limited labels on novel diseases, we show that PromptLLM can rapidly learn the corresponding knowledge for accurate novel disease reporting. The experiments on COVID-19 and diverse thorax diseases show that our approach, utilizing 1% of the training data, achieves desirable performance compared to previous methods. It shows that our approach allows us to relax the reliance on labeled data that is common to existing methods. It could have a real-world impact on data analysis during the early stages of novel diseases. Our code and data are available at https://github.com/ai-in-health/PromptLLM.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (5) , 3332-3343
Aligning, Autoencoding and Prompting Large Language Models for Novel Disease Reporting
Given radiology images, automatic radiology report generation aims to produce informative text that reports diseases. It can benefit current clinical practice in diagnostic radiology. Existing methods typically rely on large-scale medical datasets annotated by clinicians to train desirable models. However, for novel diseases, sufficient training data are typically not available. We propose a prompt-based deep learning framework, i.e., PromptLLM, to align, autoencode, and prompt the (large) language model to generate reports for novel diseases accurately and efficiently. Our method includes three major steps: (1) aligning visual images and textual reports to learn general knowledge across modalities from diseases where labeled data are sufficient, (2) autoencoding the LLM using unlabeled data of novel diseases to learn the specific knowledge and writing styles of the novel disease, and (3) prompting the LLM with learned knowledge and writing styles to report the novel diseases contained in the radiology images. Through the above three steps, with limited labels on novel diseases, we show that PromptLLM can rapidly learn the corresponding knowledge for accurate novel disease reporting. The experiments on COVID-19 and diverse thorax diseases show that our approach, utilizing 1% of the training data, achieves desirable performance compared to previous methods. It shows that our approach allows us to relax the reliance on labeled data that is common to existing methods. It could have a real-world impact on data analysis during the early stages of novel diseases. Our code and data are available at https://github.com/ai-in-health/PromptLLM.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (11) , 11000-11012
Zero-Shot Temporal Action Detection by Learning Multimodal Prompts and Text-Enhanced Actionness
Zero-shot temporal action detection (ZS-TAD), aiming to recognize and detect new and unseen video actions, is an emerging and challenging task with limited solutions. Recent studies have adapted the vision-language pre-trained model CLIP for this task in a parameter-efficient fine-tuning fashion to achieve open-vocabulary detection. However, they suffer from insufficient vision-text alignment because of the dual-stream structure of CLIP and yield inferior TAD results due to the lack of accurate action prior. In this paper, we target the above limitations and propose to learn multimodal Prompts and Text-Enhanced Actionness (mProTEA) for ZS-TAD. Specifically, we insert learnable layer-wise prompts into the vision and text branches of the frozen CLIP and establish a strong coupling between them, resulting in multimodal prompts that can boost cross-modal alignment. To ease computation costs, we propose to conduct multimodal prompt learning on an image recognition dataset with rich concepts (e.g., ImageNet) first and then keep them frozen during TAD fine-tuning. For improving TAD, we introduce text-enhanced actionness modeling, where we leverage the concise semantics of text to assist the calculation of class-agnostic actionness scores, to offer accurate prior information for both action classification and localization. With the above designs, our mProTEA excels in extensive TAD experiments, surpassing the strong competitor STALE by 5.1% on ActivityNet under the zero-shot setting and achieving state-of-the-art performance in conventional supervised scenarios. Ablation studies confirm the effectiveness of our proposals and show superior domain generalization of multimodal prompts learned on ImageNet against the other 10 image recognition datasets.
- 13 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (11) , 11000-11012
Zero-Shot Temporal Action Detection by Learning Multimodal Prompts and Text-Enhanced Actionness
Zero-shot temporal action detection (ZS-TAD), aiming to recognize and detect new and unseen video actions, is an emerging and challenging task with limited solutions. Recent studies have adapted the vision-language pre-trained model CLIP for this task in a parameter-efficient fine-tuning fashion to achieve open-vocabulary detection. However, they suffer from insufficient vision-text alignment because of the dual-stream structure of CLIP and yield inferior TAD results due to the lack of accurate action prior. In this paper, we target the above limitations and propose to learn multimodal Prompts and Text-Enhanced Actionness (mProTEA) for ZS-TAD. Specifically, we insert learnable layer-wise prompts into the vision and text branches of the frozen CLIP and establish a strong coupling between them, resulting in multimodal prompts that can boost cross-modal alignment. To ease computation costs, we propose to conduct multimodal prompt learning on an image recognition dataset with rich concepts (e.g., ImageNet) first and then keep them frozen during TAD fine-tuning. For improving TAD, we introduce text-enhanced actionness modeling, where we leverage the concise semantics of text to assist the calculation of class-agnostic actionness scores, to offer accurate prior information for both action classification and localization. With the above designs, our mProTEA excels in extensive TAD experiments, surpassing the strong competitor STALE by 5.1% on ActivityNet under the zero-shot setting and achieving state-of-the-art performance in conventional supervised scenarios. Ablation studies confirm the effectiveness of our proposals and show superior domain generalization of multimodal prompts learned on ImageNet against the other 10 image recognition datasets.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 6458-6466
Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning
While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at https://github.com/yangbang18/CLFM.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 6458-6466
Open AccessEmbracing Language Inclusivity and Diversity in CLIP through Continual Language Learning
While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at https://github.com/yangbang18/CLFM.
- Open Access
VisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding
The evolution of text to visual components facilitates people's daily lives, such as generating image, videos from text and identifying the desired elements within the images. Computer vision models involving the multimodal abilities in the previous days are focused on image detection, classification based on well-defined objects. Large language models (LLMs) introduces the transformation from nature language to visual objects, which present the visual layout for text contexts. OpenAI GPT-4 has emerged as the pinnacle in LLMs, while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models and algorithms to convert 2D images to their 3D representations. However, the mismatching between the algorithms with the problem could lead to undesired results. In response to this challenge, we propose an unified VisionGPT-3D framework to consolidate the state-of-the-art vision models, thereby facilitating the development of vision-oriented AI. VisionGPT-3D provides a versatile multimodal framework building upon the strengths of multimodal foundation models. It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts. Keywords: VisionGPT-3D, 3D vision understanding, Multimodal agent
Open AccessVisionGPT-3D: A Generalized Multimodal Agent for Enhanced 3D Vision Understanding
The evolution of text to visual components facilitates people's daily lives, such as generating image, videos from text and identifying the desired elements within the images. Computer vision models involving the multimodal abilities in the previous days are focused on image detection, classification based on well-defined objects. Large language models (LLMs) introduces the transformation from nature language to visual objects, which present the visual layout for text contexts. OpenAI GPT-4 has emerged as the pinnacle in LLMs, while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models and algorithms to convert 2D images to their 3D representations. However, the mismatching between the algorithms with the problem could lead to undesired results. In response to this challenge, we propose an unified VisionGPT-3D framework to consolidate the state-of-the-art vision models, thereby facilitating the development of vision-oriented AI. VisionGPT-3D provides a versatile multimodal framework building upon the strengths of multimodal foundation models. It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts. Keywords: VisionGPT-3D, 3D vision understanding, Multimodal agent
- Open Access
VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework
With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) as the pivot to break down users' requests into detailed action proposals to call suitable foundation models; (2) integrating multi-source outputs from foundation models automatically and generating comprehensive responses for users; (3) adaptable to a wide range of applications such as text-conditioned image understanding/generation/editing and visual question answering. This paper outlines the architecture and capabilities of VisionGPT, demonstrating its potential to revolutionize the field of computer vision through enhanced efficiency, versatility, and generalization, and performance. Our code and models will be made publicly available. Keywords: VisionGPT, Open-world visual perception, Vision-language understanding, Large language model, and Foundation model
Open AccessVisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework
With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In this paper, we introduce VisionGPT to consolidate and automate the integration of state-of-the-art foundation models, thereby facilitating vision-language understanding and the development of vision-oriented AI. VisionGPT builds upon a generalized multimodal framework that distinguishes itself through three key features: (1) utilizing LLMs (e.g., LLaMA-2) as the pivot to break down users' requests into detailed action proposals to call suitable foundation models; (2) integrating multi-source outputs from foundation models automatically and generating comprehensive responses for users; (3) adaptable to a wide range of applications such as text-conditioned image understanding/generation/editing and visual question answering. This paper outlines the architecture and capabilities of VisionGPT, demonstrating its potential to revolutionize the field of computer vision through enhanced efficiency, versatility, and generalization, and performance. Our code and models will be made publicly available. Keywords: VisionGPT, Open-world visual perception, Vision-language understanding, Large language model, and Foundation model
- Open Access
WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs
Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employs the capabilities of ChatGPT to meticulously distill and proactively construct precise prompts for each subsequent step, thereby guaranteeing the utmost accuracy in prompt communication and accurate execution in following model operations. The second part employ compatible with existing advanced diffusion techniques to expansively generate and refine the key frame at the conclusion of a video. Then we can expertly harness the power of leading and trailing key frames to craft videos with enhanced temporal consistency and action smoothness. The experimental results confirm that our method has strong effectiveness and novelty in constructing world models from text and image inputs over the other methods.
Open AccessWorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs
Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employs the capabilities of ChatGPT to meticulously distill and proactively construct precise prompts for each subsequent step, thereby guaranteeing the utmost accuracy in prompt communication and accurate execution in following model operations. The second part employ compatible with existing advanced diffusion techniques to expansively generate and refine the key frame at the conclusion of a video. Then we can expertly harness the power of leading and trailing key frames to craft videos with enhanced temporal consistency and action smoothness. The experimental results confirm that our method has strong effectiveness and novelty in constructing world models from text and image inputs over the other methods.
- 29 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (8) , 5712-5724
ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation
Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. As a result, it is necessary to collect and label data-text pairs for training, which is both costly and time-consuming. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled downstream pairs for training. During training, ZeroNLG (i) projects different domains (across modalities and languages) to corresponding coordinates in a shared common latent space; (ii) bridges different domains by aligning their corresponding coordinates in this space; and (iii) builds an unsupervised multilingual auto-encoder to learn to generate text by reconstructing the input text given its coordinate in shared latent space. Consequently, during inference, based on the data-to-text pipeline, ZeroNLG can generate target sentences across different languages given the coordinate of input data in the common space. Within this unified framework, given visual (imaging or video) data as input, ZeroNLG can perform zero-shot visual captioning; given textual sentences as input, ZeroNLG can perform zero-shot machine translation. We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and “believable” outputs and significantly outperforms existing zero-shot methods. Our code and data are available at https://github.com/yangbang18/ZeroNLG .
- 29 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (8) , 5712-5724
ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation
Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled data-to-text pairs. However, for many targeted scenarios and for non-English languages, sufficient quantities of labeled data are often not available. As a result, it is necessary to collect and label data-text pairs for training, which is both costly and time-consuming. To relax the dependency on labeled data of downstream tasks, we propose an intuitive and effective zero-shot learning framework, ZeroNLG, which can deal with multiple NLG tasks, including image-to-text (image captioning), video-to-text (video captioning), and text-to-text (neural machine translation), across English, Chinese, German, and French within a unified framework. ZeroNLG does not require any labeled downstream pairs for training. During training, ZeroNLG (i) projects different domains (across modalities and languages) to corresponding coordinates in a shared common latent space; (ii) bridges different domains by aligning their corresponding coordinates in this space; and (iii) builds an unsupervised multilingual auto-encoder to learn to generate text by reconstructing the input text given its coordinate in shared latent space. Consequently, during inference, based on the data-to-text pipeline, ZeroNLG can generate target sentences across different languages given the coordinate of input data in the common space. Within this unified framework, given visual (imaging or video) data as input, ZeroNLG can perform zero-shot visual captioning; given textual sentences as input, ZeroNLG can perform zero-shot machine translation. We present the results of extensive experiments on twelve NLG tasks, showing that, without using any labeled downstream pairs for training, ZeroNLG generates high-quality and “believable” outputs and significantly outperforms existing zero-shot methods. Our code and data are available at https://github.com/yangbang18/ZeroNLG .
- Open Access
Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning
While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at \url{https://github.com/yangbang18/CLFM}.
Open AccessEmbracing Language Inclusivity and Diversity in CLIP through Continual Language Learning
While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at \url{https://github.com/yangbang18/CLFM}.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1806-1816
Cyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding
Xuxin Cheng, Zhihong Zhu, Bang Yang, Xianwei Zhuang, Hongxiang Li, Yuexian Zou. Findings of the Association for Computational Linguistics ACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 1806-1816
Open AccessCyclical Contrastive Learning Based on Geodesic for Zero-shot Cross-lingual Spoken Language Understanding
Xuxin Cheng, Zhihong Zhu, Bang Yang, Xianwei Zhuang, Hongxiang Li, Yuexian Zou. Findings of the Association for Computational Linguistics ACL 2024. 2024.