相关论文: From Sparse Decisions to Dense Reasoning: A Multi-…

While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions.…

Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and…

The deployment of Vision-Language Models (VLMs) in safety-critical domains like autonomous driving (AD) is critically hindered by reliability failures, most notably object hallucination. This failure stems from their reliance on ungrounded,…

While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To address this gap, we introduce OmniAD, a novel framework that unifies anomaly detection and…

The rapid proliferation of multimodal social media content has driven research in Multimodal Conversational Stance Detection (MCSD), which aims to interpret users' attitudes toward specific targets within complex discussions. However,…

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial computational overhead. To address this issue, state-of-the-art…

Autonomous vehicles (AVs) are poised to redefine transportation by enhancing road safety, minimizing human error, and optimizing traffic efficiency. The success of AVs depends on their ability to interpret complex, dynamic environments…

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…

While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities. We present MIRAGE, a novel multimodal jailbreak…

We learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple…

Moral reasoning is fundamental to safe Artificial Intelligence (AI), yet ensuring its consistency across modalities becomes critical as AI systems evolve from text-based assistants to embodied agents. Current safety techniques demonstrate…

Recent advancements in large language models (LLMs) have demonstrated substantial progress in reasoning capabilities, such as DeepSeek-R1, which leverages rule-based reinforcement learning to enhance logical reasoning significantly.…

Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human…

Masked Diffusion Models (MDMs) as language models generate by iteratively unmasking tokens, yet their performance crucially depends on the inference time order of unmasking. Prevailing heuristics, such as confidence based sampling, are…

Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unified vision-language representation space. Despite their…

We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors.…

Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a…

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…

The prevalence of memes on social media has created the need to sentiment analyze their underlying meanings for censoring harmful content. Meme censoring systems by machine learning raise the need for a semi-supervised learning solution to…