相关论文: Uncertainty-guided Compositional Alignment with Pa…

Implicit spatial relations and deep semantic structures encoded in object attributes are crucial for procedural planning in embodied AI systems. However, existing approaches often over rely on the reasoning capabilities of vision language…

Unveiling visual semantics from neural signals such as EEG, MEG, and fMRI remains a fundamental challenge due to subject variability and the entangled nature of visual features. Existing approaches primarily align neural activity directly…

In recent years, the task of weakly supervised audio-visual violence detection has gained considerable attention. The goal of this task is to identify violent segments within multimodal data based on video-level labels. Despite advances in…

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize…

Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and…

Foundation models pre-trained on massive datasets, including large language models (LLMs), vision-language models (VLMs), and large multimodal models, have demonstrated remarkable success in diverse downstream tasks. However, recent studies…

The remarkable success of diffusion models in text-to-image generation has sparked growing interest in expanding their capabilities to a variety of multi-modal tasks, including image understanding, manipulation, and perception. These tasks…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

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…

Multi-modal Large Language Models (MLLMs) have recently exhibited impressive general-purpose capabilities by leveraging vision foundation models to encode the core concepts of images into representations. These are then combined with…

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limitations in VLM text encoders, particularly in areas like…

Value model guided search is effective in steering LLM generation but suffers from a lack of robustness. This is due to verifier failure: imperfect VMs mistakenly prune valid reasoning paths, especially when encountering unseen reasoning…

Learning generalizable self-supervised graph representations for downstream tasks is challenging. To this end, Contrastive Learning (CL) has emerged as a leading approach. The embeddings of CL are arranged on a hypersphere where similarity…

Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural…

Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In this paper, we analyze how unsupervised tasks can benefit…

This study evaluates the effectiveness of Vision Language Models (VLMs) in representing and utilizing multimodal content for fact-checking. To be more specific, we investigate whether incorporating multimodal content improves performance…

We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a…

As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a…

Vision-language-action (VLA) models have emerged as generalist robotic controllers capable of mapping visual observations and natural language instructions to continuous action sequences. However, VLAs provide no calibrated measure of…