Related papers: FontCode: Embedding Information in Text Documents …

Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which satisfy: (a) undetectability, a cryptographic notion…

As large language models (LLMs) grow more powerful, concerns over copyright infringement of LLM-generated texts have intensified. LLM watermarking has been proposed to trace unauthorized redistribution or resale of generated content by…

Text animation serves as an expressive medium, transforming static communication into dynamic experiences by infusing words with motion to evoke emotions, emphasize meanings, and construct compelling narratives. Crafting animations that are…

Generative models that can produce realistic images have improved significantly in recent years. The quality of the generated content has increased drastically, so sometimes it is very difficult to distinguish between the real images and…

Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a significant challenge. Our empirical analysis reveals two key observations:…

The proliferation of advanced tools for manipulating video has led to an arms race, pitting those who wish to sow disinformation against those who want to detect and expose it. Unfortunately, time favors the ill-intentioned in this race,…

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and…

In the era of deep learning, word embeddings are essential when dealing with text tasks. However, storing and accessing these embeddings requires a large amount of space. This is not conducive to the deployment of these models on…

Watermarking embeds imperceptible patterns into images for authenticity verification. However, existing methods often lack robustness against various transformations primarily including distortions, image regeneration, and adversarial…

Computer graphics seeks to deliver compelling images, generated within a computing budget, targeted at a specific display device, and ultimately viewed by an individual user. The foveated nature of human vision offers an opportunity to…

Fuzzing consists of repeatedly testing an application with modified, or fuzzed, inputs with the goal of finding security vulnerabilities in input-parsing code. In this paper, we show how to automate the generation of an input grammar…

This paper focuses on investigation of confidential documents leaks in the form of screen photographs. Proposed approach does not try to prevent leak in the first place but rather aims to determine source of the leak. Method works by…

We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence…

Scalable quantum computing and communication requires the protection of quantum information from the detrimental effects of decoherence and noise. Previous work tackling this problem has relied on the original circuit model for quantum…

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…

Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored. In this paper, we present DocMAE, a novel self-supervised framework for document…

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic…

Color coding, a technique assigning specific colors to cluster information types, has proven advantages in aiding human cognitive activities, especially reading and comprehension. The rise of Large Language Models (LLMs) has streamlined…

Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing…