相关论文: Synergistic Prompting for Robust Visual Recognitio…

Accurate knowledge of the state variables in a dynamical system is critical for effective control, diagnosis, and supervision, especially when direct measurements of all states are infeasible. This paper presents a novel approach to…

Modern recommender systems face critical challenges in handling information overload while addressing the inherent limitations of multimodal representation learning. Existing methods suffer from three fundamental limitations: (1) restricted…

Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. To address this…

Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible combinations of input data, their training efficiency suffers…

Hybrid modelling enhances the accuracy and predictive capability of dynamic models by integrating first principles with data-driven methods, effectively mitigating epistemic uncertainties inherent in mechanistic approaches. However, hybrid…

Continual learning (CL) empowers pre-trained vision-language models to adapt effectively to novel or previously underrepresented data distributions without comprehensive retraining, enhancing their adaptability and efficiency. While…

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and…

Recently, prompt tuning methods for pre-trained models have demonstrated promising performance in Class Incremental Learning (CIL). These methods typically involve learning task-specific prompts and predicting the task ID to select the…

Large language models (LLMs) have exhibited impressive abilities for multimodal content comprehension and reasoning with proper prompting in zero- or few-shot settings. Despite the proliferation of interactive systems developed to support…

The ideal goal of image matching is to achieve stable and efficient performance in unseen domains. However, many existing learning-based optical-SAR image matching methods, despite their effectiveness in specific scenarios, exhibit limited…

Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…

Multimodal deep learning has shown strong potential in medical applications by integrating heterogeneous data sources such as medical images and structured clinical variables. However, most existing approaches implicitly assume complete…

Current Retrieval-Augmented Generation systems use uniform processing, causing inefficiency as simple queries consume resources similar to complex multi-hop tasks. We present SymRAG, a framework that introduces adaptive query routing via…

Multi-modal fusion is crucial for Internet of Things (IoT) perception, widely deployed in smart homes, intelligent transport, industrial automation, and healthcare. However, existing systems often face challenges: high model complexity…

In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tasks, such as text-image classification. The growing size of…

Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

Multimodal foundation models have achieved impressive progress across a wide range of vision-language tasks. However, existing approaches often adopt fixed or task-specific fusion strategies, neglecting the intrinsic variability of modality…

Recent Vision-Language Pretrained (VLP) models have become the backbone for many downstream tasks, but they are utilized as frozen model without learning. Prompt learning is a method to improve the pre-trained VLP model by adding a…

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…