Related papers: ReasonBreak: Probing Vulnerabilities in Reasoning-…

Vision-language-action (VLA) models have advanced the field of embodied manipulation by harnessing broad world knowledge and strong generalization. However, current VLA models still face several key challenges, including limited reasoning…

Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platforms, as well as their associated power budgets, remain poorly…

Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing…

Despite their strong performance in embodied tasks, recent Vision-Language-Action (VLA) models remain highly fragile under multimodal perturbations, where visual corruption and linguistic noise jointly induce distribution shifts that…

Vision-Language-Action (VLA) models combine perception, language, and motor control in a single architecture, yet how they translate multimodal inputs into actions remains poorly understood. We apply activation injection, sparse…

Vision-language-action (VLA) models enable robots to follow natural-language instructions grounded in visual observations, but the instruction channel also introduces a critical vulnerability: small textual perturbations can alter…

Vision-Language-Action models (VLAs) achieve strong performance in general robotic manipulation tasks by scaling imitation learning. However, existing VLAs are limited to predicting short-sighted next-action, which struggle with…

Vision-language-action models (VLAs) have been extensively used in robotics applications, achieving great success in various manipulation problems. More recently, VLAs have been used in long-horizon tasks and evaluated on benchmarks, such…

Vision-language-action models (VLAs) have become increasingly popular in robot manipulation for their end-to-end design and remarkable performance. However, existing VLAs rely heavily on vision-language models (VLMs) that only support…

Ensuring the safety of vision-language models (VLMs) in autonomous driving systems is of paramount importance, yet existing research has largely focused on conventional benchmarks rather than safety-critical evaluation. In this work, we…

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome…

End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing paradigms typically fall short: autoregressive (AR) VLAs are…

Personalized driving refers to an autonomous vehicle's ability to adapt its driving behavior or control strategies to match individual users' preferences and driving styles while maintaining safety and comfort standards. However, existing…

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned…

While large multimodal models (LMMs) have demonstrated strong performance across various Visual Question Answering (VQA) tasks, certain challenges require complex multi-step reasoning to reach accurate answers. One particularly challenging…

In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such conditions, their understanding and reasoning degrade substantially, revealing a gap between clean,…

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities…

Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribution rather than inducing new capabilities, but these insights are predominantly limited to…

Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper…

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…