相关论文: Generalization Boosted Adapter for Open-Vocabulary…

Existing large language models (LLMs) that mainly focus on Standard American English (SAE) often lead to significantly worse performance when being applied to other English dialects. While existing mitigations tackle discrepancies for…

Recent advances in Large Vision-Language Models (LVLMs) have significantly improve performance in image comprehension tasks, such as formatted charts and rich-content images. Yet, Graphical User Interface (GUI) pose a greater challenge due…

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints.…

Textual adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models (VLMs) to downstream tasks. Existing works generally employ the deterministic textual feature adapter to…

Deploying Vision-Language Models (VLMs) on edge devices is challenged by resource constraints and performance degradation under distribution shifts. While test-time adaptation (TTA) can counteract such shifts, existing methods are too…

Conventional fine-tuning on domain-specific datasets can inadvertently alter a model's pretrained multimodal priors, leading to reduced generalization. To address this, we propose Chain-of-Adaptation (CoA), an adaptation framework designed…

Autonomous driving systems face significant challenges in achieving human-like adaptability, robustness, and interpretability in complex, open-world environments. These challenges stem from fragmented architectures, limited generalization…

Medical image segmentation traditionally relies on fully supervised 3D architectures that demand a large amount of dense, voxel-level annotations from clinical experts which is a prohibitively expensive process. Vision Language Models…

Vision-language models (VLMs) excel in visual understanding but often lack reliable grounding capabilities and actionable inference rates. Integrating them with open-vocabulary object detection (OVD), instance segmentation, and tracking…

Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized, heterogeneous data remains a challenge. While prompt tuning has emerged as a…

Answering semantically-complicated questions according to an image is challenging in Visual Question Answering (VQA) task. Although the image can be well represented by deep learning, the question is always simply embedded and cannot well…

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

We propose Reverse Contrast Attention (RCA), a plug-in method that enhances object localization in vision-language transformers without retraining. RCA reweights final-layer attention by suppressing extremes and amplifying mid-level…

Recent works have shown huge success of deep learning models for common in vocabulary (IV) scene text recognition. However, in real-world scenarios, out-of-vocabulary (OOV) words are of great importance and SOTA recognition models usually…

The nature of diversity in real-world environments necessitates neural network models to expand from closed category settings to accommodate novel emerging categories. In this paper, we study the open-vocabulary object detection (OVD),…

Leveraging pre-trained visual language models has become a widely adopted approach for improving performance in downstream visual question answering (VQA) applications. However, in the specialized field of medical VQA, the scarcity of…

Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers capture long-range dependencies but incur quadratic attention cost, whereas CNNs are…

Neural Network Language Models (NNLMs) for Virtual Assistants (VAs) are generally language-, region-, and in some cases, device-dependent, which increases the effort to scale and maintain them. Combining NNLMs for one or more of the…

Although recent Open-Vocabulary Object Detection architectures, such as Grounding DINO, demonstrate strong zero-shot capabilities, their performance degrades significantly under domain shifts. Moreover, many domains of practical interest,…