相关论文: Language as an Anchor: Preserving Relative Visual …

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new…

Generative zero-shot learning (ZSL) synthesizes features for unseen classes, leveraging semantic conditions to transfer knowledge from seen classes. However, it also introduces two intrinsic challenges: (1) class-level attributes fails to…

Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR solutions typically follow two regimes: enforce pairwise…

Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mismatch between text and vision modalities. We tackle this…

Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge that lies in inductive biases induced by distinct supervision…

Generalist robots should be able to understand and follow user instructions, but current vision-language-action (VLA) models struggle with following fine-grained commands despite providing a powerful architecture for mapping open-vocabulary…

Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing…

Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Concept-based models can map black-box representations to human-understandable concepts, which makes the decision-making process more transparent and then allows users to understand the reason behind predictions. However, domain-specific…

Visual entailment (VE) is to recognize whether the semantics of a hypothesis text can be inferred from the given premise image, which is one special task among recent emerged vision and language understanding tasks. Currently, most of the…

General-purpose large language models (LLMs) are increasingly deployed in verticals such as telecommunications, where adaptation is hindered by scarce, low-information-density corpora and tight mobile/edge constraints. We propose Data…

Despite the significant success of Large Vision-Language models(LVLMs), these models still suffer hallucinations when describing images, generating answers that include non-existent objects. It is reported that these models tend to…

Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors use plenty of anchors…

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the information…

Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial examples. This fragility becomes critical in real-world…

Existing deep learning-based cross-view geo-localization methods primarily focus on improving the accuracy of cross-domain image matching, rather than enabling models to comprehensively capture contextual information around the target and…

Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or…

Evaluating and Rethinking the current landscape of Large Multimodal Models (LMMs), we observe that widely-used visual-language projection approaches (e.g., Q-former or MLP) focus on the alignment of image-text descriptions yet ignore the…