A pioneering rule-based mechanical translation system (precursor of modern RBMTs) was first presented in December 1929 by its inventor, Federico Pucci, who later published the full method in a book titled "Il traduttore meccanico ed il metodo per corrispondersi fra Europei conoscendo ciascuno solo la propria lingua: Parte I", in Salerno (Italy), in 1931. This study illustrates how AI breathes new life into the system of international keys and ideograms devised by Pucci to translate from/into any Romance language (at least as a first step). The methodology involves having the AIs retranslate, following Pucci's method, the two text excerpts originally translated in 1931 and clearly documented in his publication: a passage from Dante's La Vita Nuova, translated from Italian into French, and a passage from Voltaire's Zadig, translated from French into Italian. The result is notable: the two texts, translated 94 years apart using the same method--by Pucci in 1931 and by AIs in 2025--show a low average difference, with only minor variations observed. With Pucci's system thus validated, it became feasible to have the AIs reproduce the excerpts in English, Spanish, and German according to his method. The results were consistent, and Pucci--via Artificial Intelligence--was tasked with translating more modern and technical texts, thereby reviving, nearly a century later, an invention that had remained almost entirely unknown and never applied beyond its creator, now brought to wider attention and opened to possible experimentation. Such a demonstration would not only affirm Pucci's historical status but also place him among the precursors and intellectual contributors to machine translation, whose work merits examination alongside figures such as Troyanskij, Booth, and Weaver, with possible consequences for how the history of the field is understood.

Pre-trained language models (PLMs) have substantially advanced natural language processing by providing context-sensitive text representations. However, the Algerian dialect remains under-represented, with few dedicated models available. Processing this dialect is challenging due to its complex morphology, frequent code-switching, multiple scripts, and strong lexical influences from other languages. These characteristics complicate tokenization and reduce the effectiveness of conventional word- or subword-level approaches. To address this gap, we introduce chDzDT, a character-level pre-trained language model tailored for Algerian morphology. Unlike conventional PLMs that rely on token sequences, chDzDT is trained on isolated words. This design allows the model to encode morphological patterns robustly, without depending on token boundaries or standardized orthography. The training corpus draws from diverse sources, including YouTube comments, French, English, and Berber Wikipedia, as well as the Tatoeba project. It covers multiple scripts and linguistic varieties, resulting in a substantial pre-training workload. Our contributions are threefold: (i) a detailed morphological analysis of Algerian dialect using YouTube comments; (ii) the construction of a multilingual Algerian lexicon dataset; and (iii) the development and extensive evaluation of a character-level PLM as a morphology-focused encoder for downstream tasks. The proposed approach demonstrates the potential of character-level modeling for morphologically rich, low-resource dialects and lays a foundation for more inclusive and adaptable NLP systems.

The paper presents an approach in which inertial signals measured with a wrist-worn sensor (e.g., a smartwatch) are translated into those that would be recorded using a shoe-mounted sensor, enabling the use of state-of-the-art gait analysis methods. In the study, the signals are translated using Conditional Generative Adversarial Networks (GANs). Two different GAN versions are used for experimental verification: traditional ones trained using binary cross-entropy loss and Wasserstein GANs (WGANs). For the generator, two architectures, a convolutional autoencoder, and a convolutional U-Net, are tested. The experiment results have shown that the proposed approach allows for an accurate translation, enabling the use of wrist sensor inertial signals for efficient, every-day gait analysis.

We present CrossTL, a universal programming language translator enabling bidirectional translation between multiple languages through a unified intermediate representation called CrossGL. Traditional approaches require separate translators for each language pair, leading to exponential complexity growth. CrossTL uses a single universal IR to facilitate translations between CUDA, HIP, Metal, DirectX HLSL, OpenGL GLSL, Vulkan SPIR-V, Rust, and Mojo, with Slang support in development. Our system consists of: language-specific lexers/parsers converting source code to ASTs, bidirectional CrossGL translation modules implementing ToCrossGLConverter classes for importing code and CodeGen classes for target generation, and comprehensive backend implementations handling full translation pipelines. We demonstrate effectiveness through comprehensive evaluation across programming domains, achieving successful compilation and execution across all supported backends. The universal IR design enables adding new languages with minimal effort, requiring only language-specific frontend/backend components. Our contributions include: (1) a unified IR capturing semantics of multiple programming paradigms, (2) a modular architecture enabling extensibility, (3) a comprehensive framework supporting GPU compute, graphics programming, and systems languages, and (4) empirical validation demonstrating practical viability of universal code translation. CrossTL represents a significant step toward language-agnostic programming, enabling write-once, deploy-everywhere development.

Autoregressive language models are vulnerable to orthographic attacks, where input text is perturbed with characters from multilingual alphabets, leading to substantial performance degradation. This vulnerability primarily stems from the out-of-vocabulary issue inherent in subword tokenizers and their embeddings. To address this limitation, we propose a pixel-based generative language model that replaces the text-based embeddings with pixel-based representations by rendering words as individual images. This design provides stronger robustness to noisy inputs, while an extension of compatibility to multilingual text across diverse writing systems. We evaluate the proposed method on the multilingual LAMBADA dataset, WMT24 dataset and the SST-2 benchmark, demonstrating both its resilience to orthographic noise and its effectiveness in multilingual settings.

Quantization is essential for deploying large language models (LLMs) on resource-constrained hardware, but its implications for multilingual tasks remain underexplored. We conduct the first large-scale evaluation of post-training quantization (PTQ) on machine translation across 55 languages using five LLMs ranging from 1.7B to 70B parameters. Our analysis reveals that while 4-bit quantization often preserves translation quality for high-resource languages and large models, significant degradation occurs for low-resource and typologically diverse languages, particularly in 2-bit settings. We compare four quantization techniques (AWQ, BitsAndBytes, GGUF, and AutoRound), showing that algorithm choice and model size jointly determine robustness. GGUF variants provide the most consistent performance, even at 2-bit precision. Additionally, we quantify the interactions between quantization, decoding hyperparameters, and calibration languages, finding that language-matched calibration offers benefits primarily in low-bit scenarios. Our findings offer actionable insights for deploying multilingual LLMs for machine translation under quantization constraints, especially in low-resource settings.

Machine translation quality has steadily improved over the years, achieving near-perfect translations in recent benchmarks. These high-quality outputs make it difficult to distinguish between state-of-the-art models and to identify areas for future improvement. In this context, automatically identifying texts where machine translation systems struggle holds promise for developing more discriminative evaluations and guiding future research. In this work, we address this gap by formalizing the task of translation difficulty estimation, defining a text's difficulty based on the expected quality of its translations. We introduce a new metric to evaluate difficulty estimators and use it to assess both baselines and novel approaches. Finally, we demonstrate the practical utility of difficulty estimators by using them to construct more challenging benchmarks for machine translation. Our results show that dedicated models outperform both heuristic-based methods and LLM-as-a-judge approaches, with Sentinel-src achieving the best performance. Thus, we release two improved models for difficulty estimation, Sentinel-src-24 and Sentinel-src-25, which can be used to scan large collections of texts and select those most likely to challenge contemporary machine translation systems.

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena across sentences and paragraphs. In this work, we propose a method to improve LLM-based long-document translation through targeted fine-tuning on high-quality document-level data, which we curate and introduce as DocBlocks. Our approach supports multiple translation paradigms, including direct document-to-document and chunk-level translation, by integrating instructions both with and without surrounding context. This enables models to better capture cross-sentence dependencies while maintaining strong sentence-level translation performance. Experimental results show that incorporating multiple translation paradigms improves document-level translation quality and inference speed compared to prompting and agent-based methods.

Multilingual machine translation (MT) benchmarks play a central role in evaluating the capabilities of modern MT systems. Among them, the FLORES+ benchmark is widely used, offering English-to-many translation data for over 200 languages, curated with strict quality control protocols. However, we study data in four languages (Asante Twi, Japanese, Jinghpaw, and South Azerbaijani) and uncover critical shortcomings in the benchmark's suitability for truly multilingual evaluation. Human assessments reveal that many translations fall below the claimed 90% quality standard, and the annotators report that source sentences are often too domain-specific and culturally biased toward the English-speaking world. We further demonstrate that simple heuristics, such as copying named entities, can yield non-trivial BLEU scores, suggesting vulnerabilities in the evaluation protocol. Notably, we show that MT models trained on high-quality, naturalistic data perform poorly on FLORES+ while achieving significant gains on our domain-relevant evaluation set. Based on these findings, we advocate for multilingual MT benchmarks that use domain-general and culturally neutral source texts rely less on named entities, in order to better reflect real-world translation challenges.

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.