Related papers: Strong Copyright Protection for Language Models vi…

Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the "factorization barrier": the assumption that simultaneously predicted tokens are independent. This limitation forces a…

The widespread deployment of large vision models such as Stable Diffusion raises significant legal and ethical concerns, as these models can memorize and reproduce copyrighted content without authorization. Existing detection approaches…

Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from…

With the growing demand for protecting the intellectual property (IP) of text-to-image diffusion models, we propose PCDiff -- a proactive access control framework that redefines model authorization by regulating generation quality. At its…

The widespread use of large language models has resulted in a multitude of tokenizers and embedding spaces, making knowledge transfer in prompt discovery tasks difficult. In this work, we propose FUSE (Flexible Unification of Semantic…

Neural networks are rapidly gaining popularity in scientific research, but training the models is often very time-consuming. Particularly when the training data samples are large high-dimensional arrays, efficient training methodologies…

Cultural heritage applications and advanced machine learning models are creating a fruitful synergy to provide effective and accessible ways of interacting with artworks. Smart audio-guides, personalized art-related content and gamification…

Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and…

Large Language Models (LLMs) show promise for automated code repair but often struggle with the complex semantic and structural correctness required. We present SynthFix, a hybrid neural-symbolic framework that improves LLM-based…

Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as…

In recent years, with the development of quantum machine learning, quantum neural networks (QNNs) have gained increasing attention in the field of natural language processing (NLP) and have achieved a series of promising results. However,…

Lexically cohesive translations preserve consistency in word choices in document-level translation. We employ a copy mechanism into a context-aware neural machine translation model to allow copying words from previous translation outputs.…

Recent advancements in large language models have revolutionized text generation with their remarkable capabilities. These models can produce controlled texts that closely adhere to specific requirements when prompted appropriately.…

Federated learning (FL) has sparked extensive interest in exploiting the private data on clients' local devices. However, the parameter server setting of FL not only has high bandwidth requirements, but also poses data privacy issues and a…

Recent advancements in diffusion models revolutionize image generation but pose risks of misuse, such as replicating artworks or generating deepfakes. Existing image protection methods, though effective, struggle to balance protection…

In Bag-of-Words (BoW) based image retrieval, the SIFT visual word has a low discriminative power, so false positive matches occur prevalently. Apart from the information loss during quantization, another cause is that the SIFT feature only…

The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on apparently benign data for downstream tasks can jeopardize…

We study hybrid search in text retrieval where lexical and semantic search are fused together with the intuition that the two are complementary in how they model relevance. In particular, we examine fusion by a convex combination (CC) of…

Transferring human motion from a source to a target person poses great potential in computer vision and graphics applications. A crucial step is to manipulate sequential future motion while retaining the appearance characteristic.Previous…

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise.…