Related papers: Hierarchical Refinement of Universal Multimodal At…

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial…

Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a…

Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics. One fundamental challenge is the lack of robotic data,…

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models.…

Vision-language pre-training (VLP) models are vulnerable to adversarial examples, particularly in black-box scenarios. Existing multimodal attacks often suffer from limited perturbation diversity and unstable multi-stage pipelines. To…

Vision-Language-Action (VLA) models offer promising capabilities for autonomous driving through multimodal understanding. However, their utilization in safety-critical scenarios is constrained by inherent limitations, including imprecise…

Text-based person anomaly retrieval has emerged as a challenging task, with most existing approaches relying on complex deep-learning techniques. This raises a research question: How can the model be optimized to achieve greater…

The integration of visual and textual data in Vision-Language Pre-training (VLP) models is crucial for enhancing vision-language understanding. However, the adversarial robustness of these models, especially in the alignment of image-text…

Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent attacks based on input transformations, such as random cropping, suggest that spatially…

Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic…

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

Recently, point-supervised temporal action localization has gained significant attention for its effective balance between labeling costs and localization accuracy. However, current methods only consider features from visual inputs,…

Vision Language Models (VLMs) have undergone significant advancements, particularly with the emergence of mobile-oriented VLMs, which offer a wide range of application scenarios. However, the substantial computational requirements for…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Existing alignment techniques for Large Language Models (LLMs), such as Direct Preference Optimization (DPO), typically treat the model as a monolithic entity, applying uniform optimization pressure across all layers. This approach…

We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the…

Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in…

Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic hierarchical rules that are agnostic to…

Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgoals. The main challenge of HRL is efficient discovery of the…