Related papers: CoCoA-Mix: Confusion-and-Confidence-Aware Mixture …
Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and…
No-reference point cloud quality assessment (NR-PCQA) aims to automatically evaluate the perceptual quality of distorted point clouds without available reference, which have achieved tremendous improvements due to the utilization of deep…
Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the…
Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models…
Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based…
Commit Classification(CC) is an important task in software maintenance since it helps software developers classify code changes into different types according to their nature and purpose. This allows them to better understand how their…
Learning-based image dehazing algorithms have shown remarkable success in synthetic domains. However, real image dehazing is still in suspense due to computational resource constraints and the diversity of real-world scenes. Therefore,…
Camouflaged Object Detection (COD) aims to segment objects that blend seamlessly into complex backgrounds, with growing interest in exploiting additional visual modalities to enhance robustness through complementary information. However,…
Large language models (LLMs) have shown great potential in medical question answering (MedQA), yet adapting them to biomedical reasoning remains challenging due to domain-specific complexity and limited supervision. In this work, we study…
Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications…
The potential for zero-shot generalization in vision-language (V-L) models such as CLIP has spurred their widespread adoption in addressing numerous downstream tasks. Previous methods have employed test-time prompt tuning to adapt the model…
We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material. While other approaches find correspondences between pairs of images by treating…
Merging neural networks without retraining is central to federated and distributed learning. Common methods such as weight averaging or Fisher merging often lose accuracy and are unstable across seeds. CoGraM (Contextual Granular Merging)…
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based…
Although fusing multiple sensor modalities can enhance object detection performance, existing fusion approaches often overlook subtle variations in environmental conditions and sensor inputs. As a result, they struggle to adaptively weight…
Mammalian brains handle complex reasoning by integrating information across brain regions specialized for particular sensory modalities. This enables improved robustness and generalization versus deep neural networks, which typically…
Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after generating an answer, which measure the correctness of a specific…
Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods typically employ a single window length across all attention…
Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends…
Standard Large Language Model (LLM) pre-training typically treats corpora as flattened token sequences, often overlooking the real-world context that humans naturally rely on to contextualize information. To bridge this gap, we introduce…