相关论文: Invisible Entropy: Towards Safe and Efficient Low-…

Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they produce, such as…

Recent studies improve on-device language model (LM) inference through end-cloud collaboration, where the end device retrieves useful information from cloud databases to enhance local processing, known as Retrieval-Augmented Generation…

While Generative AI stands to be one of the fastest adopted technologies ever, studies have made evident that the usage of Large Language Models (LLMs) puts significant burden on energy grids and our environment. It may prove a hindrance to…

Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic,…

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 Language Models (LLMs) have demonstrated remarkable capabilities, but their training requires extensive data and computational resources, rendering them valuable digital assets. Therefore, it is essential to watermark LLMs to protect…

Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs. While predictive entropy provides a strong baseline for…

To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have…

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private…

Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial? Empirical evidence reveals a striking…

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

Watermarking is a technical alternative to safeguarding intellectual property and reducing misuse. Existing methods focus on optimizing watermarked latent variables to balance watermark robustness and fidelity, as Latent diffusion models…

As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and…

Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur high computational costs. Token-based watermarking…

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time…

Balanced and efficient information flow is essential for optimizing language generation models. In this work, we propose Entropy-UID, a new token selection method that balances entropy and Uniform Information Density (UID) principles for…

Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap…

From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models (LLMs). However, large-scale web scraping to feed LLMs can affect site…

Uncertainty estimation in multi-LLM systems remains largely single-model-centric: existing methods quantify uncertainty within each model but do not adequately capture semantic disagreement across models. To address this gap, we propose…