相关论文: MultiPriv: Benchmarking Individual-Level Privacy R…

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts.…

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…

Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of…

Exploring the mysteries of the human brain is a long-term research topic in neuroscience. With the help of deep learning, decoding visual information from human brain activity fMRI has achieved promising performance. However, these decoding…

The ability to distinguish subtle differences between visually similar images is essential for diverse domains such as industrial anomaly detection, medical imaging, and aerial surveillance. While comparative reasoning benchmarks for…

Multimodal large language models (MLLMs) have shown great potential in perception and interpretation tasks, but their capabilities in predictive reasoning remain under-explored. To address this gap, we introduce a novel benchmark that…

Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are…

With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Large language models (LLMs) are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer significant technological progress, their development using vast…

AI models have achieved state-of-the-art results in textual reasoning; however, their ability to reason over spatial and relational structures remains a critical bottleneck -- particularly in early-grade maths, which relies heavily on…

The emergence of large language models (LLMs), and their increased use in user-facing systems, has led to substantial privacy concerns. To date, research on these privacy concerns has been model-centered: exploring how LLMs lead to privacy…

Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…

The rapid advancement of Visual Language Models (VLMs) has enabled sophisticated analysis of visual content, leading to concerns about the inference of sensitive user attributes and subsequent privacy risks. While technical capabilities of…

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…

Despite advances in the field of privacy-preserving Natural Language Processing (NLP), a significant challenge remains the accurate evaluation of privacy. As a potential solution, using LLMs as a privacy evaluator presents a promising…

Multimodal Large Language Models (MLLMs) serve as daily assistants for millions. However, their ability to generate responses aligned with individual preferences remains limited. Prior approaches enable only static, single-turn…

Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this…

Learning systems that preserve privacy often inject noise into hierarchical visual representations; a central challenge is to \emph{model} how such perturbations align with a declared privacy budget in a way that is interpretable and…