相关论文: Attention Misses Visual Risk: Risk-Adaptive Steeri…

Multimodal Face Anti-Spoofing (FAS) methods, which integrate multiple visual modalities, often suffer even more severe performance degradation than unimodal FAS when deployed in unseen domains. This is mainly due to two overlooked risks…

Semantic segmentation allows autonomous driving cars to understand the surroundings of the vehicle comprehensively. However, it is also crucial for the model to detect obstacles that may jeopardize the safety of autonomous driving systems.…

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…

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow…

Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods typically rely on the unrealistic assumption of full-modal availability during training…

From clinical healthcare to daily living, continuous sensor monitoring across multiple modalities has shown great promise for real-world intelligent decision-making but also faces various challenges. In this work, we introduce MAESTRO, a…

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Large Language Model (LLM)-powered multi-agent systems (MAS) have rapidly advanced collaborative reasoning, tool use, and role-specialized coordination in complex tasks. However, reliability-critical deployment remains hindered by a…

Referring Image Segmentation (RIS) aims to segment the object in an image uniquely referred to by a natural language expression. However, RIS training often contains hard-to-align and instance-specific visual signals; optimizing on such…

For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments. These external and environmental factors, along with internal factors associated with…

As the horizon of intelligent transportation expands with the evolution of Automated Driving Systems (ADS), ensuring paramount safety becomes more imperative than ever. Traditional risk assessment methodologies, primarily crafted for…

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue,…

Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…

In the domain of multimodal intent recognition (MIR), the objective is to recognize human intent by integrating a variety of modalities, such as language text, body gestures, and tones. However, existing approaches face difficulties…

Reachability analysis has become increasingly important in robotics to distinguish safe from unsafe states. Unfortunately, existing reachability and safety analysis methods often fall short, as they typically require known system dynamics…

Inspired by human visual attention, we propose a novel inverse reinforcement learning formulation using Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) for predicting the visual attention of drivers in accident-prone…

Safe navigation is essential for autonomous systems operating in hazardous environments. Traditional planning methods excel at long-horizon tasks but rely on a predefined graph with fixed distance metrics. In contrast, safe Reinforcement…

Multimodal multiview learning seeks to integrate information from diverse sources to enhance task performance. Existing approaches often struggle with flexible view configurations, including arbitrary view combinations, numbers of views,…

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

This paper addresses security challenges in multi-robot systems (MRS) where adversaries may compromise robot control, risking unauthorized access to forbidden areas. We propose a novel multi-robot optimal planning algorithm that integrates…