Related papers: Faster Post-Quantum TLS 1.3 Based on ML-KEM: Imple…

Quantum computer is no longer a hypothetical idea. It is the worlds most important technology and there is a race among countries to get supremacy in quantum technology. Its the technology that will reduce the computing time from years to…

Quality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. We show that State-of-the-art QE…

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Multi Task Learning (MTL) efficiently leverages useful information contained in multiple related tasks to help improve the generalization performance of all tasks. This article conducts a large dimensional analysis of a simple but, as we…

QUIC has rapidly evolved into a cornerstone transport protocol for secure, low-latency communications, yet its deployment continues to expose critical security and privacy vulnerabilities, particularly during connection establishment phases…

The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…

Traditional cryptographic techniques, including token obfuscation, are increasingly vulnerable to quantum attacks due to advancements in quantum computing. Quantum algorithms such as Shor's and Grover's pose significant threats to classical…

Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervised fine-tuning (SFT) approach, which relies on large-scale…

Quantum Key Distribution (QKD) is a promising technique for ensuring long-term security in communication systems. Unlike conventional key exchange methods like RSA, which quantum computers could theoretically break [1], QKD offers enhanced…

Quantum key distribution (QKD) has emerged as a critical component of secure communication in the quantum era, ensuring information-theoretic security. Despite its potential, there are issues in optimizing key generation rates, enhancing…

Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to its context memory using an approach called token recycling.…

The traditional way for a Quantum Key Distribution (QKD) user to join a quantum network is by authenticating themselves using pre-shared key material. While this approach is sufficient for small-scale networks, it becomes impractical as the…

Prediction for ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) plays a crucial role in drug discovery and development, accelerating the screening and optimization of new drugs. Existing methods primarily rely on…

Classification techniques can be used to analyze system behaviors, network protocols, and cryptographic primitives based on identifiable traits. While useful for defense, such classification can also be leveraged by attackers to infer…

Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache grows, it becomes a major memory and computation bottleneck. However, there is an opportunity to…

Transportation Cyber-Physical Systems (TCPS) integrate physical elements, such as transportation infrastructure and vehicles, with cyber elements via advanced communication technologies, allowing them to interact seamlessly. This…

Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…

Autoregressive large language models (LLMs) generate text token-by-token, requiring n forward passes to produce a sequence of length n. Recent work, Exploring the Latent Capacity of LLMs for One-Step Text Reconstruction (Mezentsev and…

We propose a new model architecture specifically suited for text-to-speech (TTS) models. We combine WavLM, a pre-trained self-supervised learning (SSL) speech model, and the BEST-RQ vector quantization framework. We assess the extent to…

Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods…