相关论文: VLA-Mark: A cross modal watermark for large vision…

Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs are relatively mature, extending them to open-source models…

Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich…

While text-to-image (T2I) generation models have achieved remarkable progress in recent years, existing evaluation methodologies for vision-language alignment still struggle with the fine-grained semantic matching. Current approaches based…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they rely either on simple superposition in the noise space or…

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for safe semantic reasoning and decision-making. While recent VLMs demonstrate strong performance…

Multimodal Large Language Models (MLLMs) excel at descriptive tasks within images but often struggle with precise object localization, a critical element for reliable visual interpretation. In contrast, traditional object detection models…

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely…

Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from…

As large language models become increasingly capable and widely deployed, verifying the provenance of machine-generated content is critical to ensuring trust, safety, and accountability. Watermarking techniques have emerged as a promising…

Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by large language models (LLMs) or even unauthorized training of…

Visual Grounding (VG) aims to utilize given natural language queries to locate specific target objects within images. While current transformer-based approaches demonstrate strong localization performance in standard scene (i.e, scenarios…

Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior performance. While existing…

The recent advancements in large language models (LLMs) have sparked a growing apprehension regarding the potential misuse. One approach to mitigating this risk is to incorporate watermarking techniques into LLMs, allowing for the tracking…

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

With the increasing use of large language models (LLMs) in daily life, concerns have emerged regarding their potential misuse and societal impact. Watermarking is proposed to trace the usage of specific models by injecting patterns into…

The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…