相关论文: Goal-oriented Backdoor Attack against Vision-Langu…

Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming. However, we…

Multi-modal large language models (MLLMs) extend large language models (LLMs) to process multi-modal information, enabling them to generate responses to image-text inputs. MLLMs have been incorporated into diverse multi-modal applications,…

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

With the thriving of deep learning in processing point cloud data, recent works show that backdoor attacks pose a severe security threat to 3D vision applications. The attacker injects the backdoor into the 3D model by poisoning a few…

While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place…

Recently, Vision-Language-Action (VLA) models have demonstrated strong performance on a range of robotic tasks. These models rely on multimodal inputs, with language instructions playing a crucial role -- not only in predicting actions, but…

Backdoor attacks pose a significant threat to deep neural networks, as backdoored models would misclassify poisoned samples with specific triggers into target classes while maintaining normal performance on clean samples. Among these,…

Skeleton Action Recognition (SAR) has attracted significant interest for its efficient representation of the human skeletal structure. Despite its advancements, recent studies have raised security concerns in SAR models, particularly their…

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in robotic manipulation,enabling robots to execute natural language commands through end-to-end learning from visual observations.However, deploying large-scale…

In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing…

Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However,…

Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely…

Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for…

Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle…

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on…

Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between reasoning and trajectory generation. However, the robustness of such systems under…

3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues of 3D deep models. Although most of them consider adversarial…

Understanding the vulnerabilities of Large Vision Language Models (LVLMs) to jailbreak attacks is essential for their responsible real-world deployment. Most previous work requires access to model gradients, or is based on human knowledge…

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…