相关论文: HeBA: Heterogeneous Bottleneck Adapters for Robust…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic knowledge embedded in Large Language Models (LLMs). However, existing approaches typically rely…

Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation by grounding high-level semantic instructions into executable physical actions. However, prevailing approaches typically adopt a monolithic…

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of…

While recent vision-and-language models (VLMs) like CLIP are a powerful tool for analyzing text and images in a shared semantic space, they do not explicitly model the hierarchical nature of the set of texts which may describe an image.…

Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention…

Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual-textual alignment through biased token selection and static…

Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or…

Molecular representation learning, a cornerstone for downstream tasks like molecular captioning and molecular property prediction, heavily relies on Graph Neural Networks (GNN). However, GNN suffers from the over-smoothing problem, where…

Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications. Existing well-established methods often struggle to attain this goal due to…

Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish…

Recent advances in representation learning have shown that hyperbolic geometry can offer a more expressive alternative to the Euclidean embeddings used in CLIP models, capturing hierarchical structures and leading to better-organized…

We propose Context-Adaptive Multi-Prompt Embedding, a novel approach to enrich semantic representations in vision-language contrastive learning. Unlike standard CLIP-style models that rely on a single text embedding, our method introduces…

Visual foundation models like CLIP excel in learning feature representations from extensive datasets through self-supervised methods, demonstrating remarkable transfer learning and generalization capabilities. A growing number of…

In this paper, we propose EventBind, a novel and effective framework that unleashes the potential of vision-language models (VLMs) for event-based recognition to compensate for the lack of large-scale event-based datasets. In particular,…

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do…

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…

Heterogeneous multi-modal remote sensing object detection aims to accurately detect objects from diverse sensors (e.g., RGB, SAR, Infrared). Existing approaches largely adopt a late alignment paradigm, in which modality alignment and…

The development of foundation models for embodied intelligence critically depends on access to large-scale, high-quality robot demonstration data. Recent approaches have sought to address this challenge by training on large collections of…

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse…