A BSTRACT In the looming post-quantum era, traditional cryptographic systems are increasingly vulnerable to quantum computing attacks that can compromise their mathematical foundations. To address this critical challenge, we propose crypto-ncRNA--a bio-convergent cryptographic framework that leverages the dynamic folding properties of non-coding RNA (ncRNA) to generate high-entropy, quantum-resistant keys and produce unpredictable ciphertexts. The framework employs a novel, multi-stage process: encoding plaintext into RNA sequences, predicting and manipulating RNA secondary structures using advanced algorithms, and deriving cryptographic keys through the intrinsic physical unclonability of RNA molecules. Experimental evaluations indicate that, although cryptoncRNA's encryption speed is marginally lower than that of AES, it significantly outperforms RSA in terms of efficiency and scalability while achieving a 100% pass rate on the NIST SP 800-22 randomness tests. These results demonstrate that crypto-ncRNA offers a promising and robust approach for securing digital infrastructures against the evolving threats posed by quantum computing. Moreover, with the rapid advancement of artificial intelligence, RNA-based research has gradually unfolded into a new realm of innovation (Townshend et al. (2021)). Recent studies showed that the dynamic folding processes of RNA molecules intrinsically exhibit physical unclonable functions (PUFs) characteristics (Herder et al. (2014); Li et al. (2022); Luescher et al. (2024); Zhou et al. (2021)), thereby establishing a pathway for designing post-quantum cryptography (PQC) systems (Arapinis et al. (2021); Cambou et al. (2021)).

The ability to quickly and accurately identify microbial species in a sample, known as metagenomic profiling, is critical across various fields, from healthcare to environmental science. This paper introduces a novel method to profile signals coming from sequencing devices in parallel with determining their nucleotide sequences, a process known as basecalling, via a multi-objective deep neural network for simultaneous basecalling and multi-class genome classification. We introduce a new loss strategy where losses for basecalling and classification are back-propagated separately, with model weights combined for the shared layers, and a pre-configured ranking strategy allowing top-K species accuracy, giving users flexibility to choose between higher accuracy or higher speed at identifying the species. We achieve state-of-the-art basecalling accuracies, while classification accuracies meet and exceed the results of state-of-the-art binary classifiers, attaining an average of 92.5%/98.9% accuracy at identifying the top-1/3 species among a total of 17 genomes in the Wick bacterial dataset. The work presented here has implications for future studies in metagenomic profiling by accelerating the bottleneck step of matching the DNA sequence to the correct genome.

Recently, Probabilistic Language-Image Pre-Training (ProLIP) has been proposed to tackle the multiplicity issue of vision-language (VL) tasks. Despite their success in probabilistic representation learning at a scale, the ProLIP models cannot handle long context texts longer than 64 context length, which limits their ability to capture rich contextual information from longer text sequences. To address this issue, this paper proposes a fine-tuning strategy for ProLIP to accept longer texts, e.g., 256 text tokens. Experimental results on Urban-1k and the DataComp evaluation suite show that the proposed LongProLIP recipe can improve understanding of long contexts while minimizing the negative effect of fine-tuning.We also observe a trade-off between the long context understanding (measured by Urban-1k) and general zero-shot capability (measured by evaluation datasets by DataComp). Code is available at https://github.com/naver-ai/prolip

We also present the baselines, datasets details, C 3 batchwise performance λ selection details, and experimental setup. A.1 R EPRESENTING THE CURRENT DERIVATIVE WITH THE F ISHER INFORMATION MATRIX Let us consider having a model with parameter θ and a likelihood function p (X | θ), where X is observed data. The estimate of true parameter θ can be found by using estimator ˆ θ . The Fisher information I (θ) can be defined as the expected value of the negative hessian of the log-likelihood function. I (θ) = E null 2 log p (X | θ) θ θ T null (4) The Cram er-Rao Lower Bound (CRLB) states that for any unbiased estimator ˆ θ, the variance-covariance matrix V ( ˆ θ) satisfies the inequality property: V ( ˆ θ) I 1 (θ) (5) The symbol represents the following matrix inequality V ( ˆ θ) I 1 (θ) positive and semi-definite.

This paper introduces a simple extension of mixup (Zhang et al., 2018) data augmentation to enhance generalization in visual recognition tasks. Unlike the vanilla mixup method, which blends entire images, our approach focuses on combining regions from multiple images. Mixup (Zhang et al., 2018) is a data augmentation method that trains models on weighted averages of randomly paired training points. The averaging weights are typically sampled from a beta distribution with parameter α, where α ensures that the generated training set remains close to the original dataset. Mixup-generated perturbations may adhere only to the direction towards any arbitrary data point, potentially resulting in suboptimal regularization (Guo et al., 2019).

We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models. Although existing works showed that watermarking can be robust for natural language, we show that it is easy to remove these watermarks on code by semantic-preserving transformations.

This paper presents CrossVoice, a novel cascade-based Speech-to-Speech Translation (S2ST) system employing advanced ASR, MT, and TTS technologies with cross-lingual prosody preservation through transfer learning. We conducted comprehensive experiments comparing CrossVoice with direct-S2ST systems, showing improved BLEU scores on tasks such as Fisher Es-En, VoxPopuli Fr-En and prosody preservation on benchmark datasets CVSS-T and IndicTTS. With an average mean opinion score of 3.6 out of 4, speech synthesized by CrossVoice closely rivals human speech on the benchmark highlighting the efficacy of cascade-based systems and transfer learning in multilingual S2ST with prosody transfer. Transformer-based models (Vaswani et al., 2017) have revolutionized speech processing, leading to significant advancements in automatic speech recognition and text-to-speech technologies (Latif et al., 2023; Prabhavalkar et al., 2023). This shift towards end-to-end systems has opened new avenues in Speech-to-Speech Translation (S2ST) for translating speech across languages.

The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e., Supervised Fine-Tuning (SFT) and Transfer Learning (TL). This comparison utilizes three distinct metrics: Mean Opinion Score (MOS), Recognition Accuracy (RA), and Mel Cepstral Distortion (MCD). Results demonstrate that, in comparison to SFT, TL leads to significantly enhanced performance, with an average MOS higher by 1.53 points, a 37.5% increase in RA, and approximately, a 7.8-point improvement in MCD. These findings are instrumental in helping build TTS models for low-resource languages.

The increasing adoption of solar energy necessitates advanced methodologies for monitoring and maintenance to ensure optimal performance of solar panel installations. A critical component in this context is the accurate segmentation of solar panels from aerial or satellite imagery, which is essential for identifying operational issues and assessing efficiency. This paper addresses the significant challenges in panel segmentation, particularly the scarcity of annotated data and the labour-intensive nature of manual annotation for supervised learning. We explore and apply Self-Supervised Learning (SSL) to solve these challenges. We demonstrate that SSL significantly enhances model generalization under various conditions and reduces dependency on manually annotated data, paving the way for robust and adaptable solar panel segmentation solutions.

Large Language Models (LLMs) hold the potential to revolutionize autoformalization. The introduction of Lean4, a mathematical programming language, presents an unprecedented opportunity to rigorously assess the autoformalization capabilities of LLMs. This paper introduces a novel evaluation benchmark designed for Lean4, applying it to test the abilities of state-of-the-art LLMs, including GPT-3.5, GPT-4, and Gemini Pro. Our comprehensive analysis reveals that, despite recent advancements, these LLMs still exhibit limitations in autoformalization, particularly in more complex areas of mathematics. These findings underscore the need for further development in LLMs to fully harness their potential in scientific research and development. This study not only benchmarks current LLM capabilities but also sets the stage for future enhancements in autoformalization.