Privacy-Preserving Real-Time Vietnamese-English Translation on iOS using Edge AI

• URL: http://arxiv.org/abs/2505.07583v1
• Date: Mon, 12 May 2025 14:05:39 GMT
• Title: Privacy-Preserving Real-Time Vietnamese-English Translation on iOS using Edge AI
• Abstract summary: This project confronts challenges in deploying complex NMT models on resource-limited mobile devices.<n>The application is realized as a real-time iOS prototype, tightly integrating modern iOS frameworks and privacy-by-design principles.
• Score: 0.6526824510982802
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This research addresses the growing need for privacy-preserving and accessible language translation by developing a fully offline Neural Machine Translation (NMT) system for Vietnamese-English translation on iOS devices. Given increasing concerns about data privacy and unreliable network connectivity, on-device translation offers critical advantages. This project confronts challenges in deploying complex NMT models on resource-limited mobile devices, prioritizing efficiency, accuracy, and a seamless user experience. Leveraging advances such as MobileBERT and, specifically, the lightweight \textbf{TinyLlama 1.1B Chat v1.0} in GGUF format, \textbf{a} quantized Transformer-based model is implemented and optimized. The application is realized as a real-time iOS prototype, tightly integrating modern iOS frameworks and privacy-by-design principles. Comprehensive documentation covers model selection, technical architecture, challenges, and final implementation, including functional Swift code for deployment.

Related papers

• A Pilot Study on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights [27.632954643254884]
  Large Language Models (LLMs) were recently leveraged to enhance code translation at different granularities.<n>This study aims to fill this gap by evaluating LLM-based agentic approaches for mobile application translation.<n>We developed a chain of agents that account for dependencies, specifications, program structure, and program control flow.
  arXiv  Detail & Related papers  (2025-07-21T20:11:01Z)
• Apple Intelligence Foundation Language Models: Tech Report 2025 [246.04717786298764]
  We introduce two foundation language models that power Apple Intelligence features across Apple devices and services.<n>Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling.<n>A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning.
  arXiv  Detail & Related papers  (2025-07-17T23:37:19Z)
• CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering [68.91862701376155]
  CoSteer is a novel collaborative framework that enables decoding-time personalization through localized delta steering.<n>We formulate token-level optimization as an online learning problem, where local delta vectors dynamically adjust the remote LLM's logits.<n>This approach preserves privacy by transmitting only the final steered tokens rather than raw data or intermediate vectors.
  arXiv  Detail & Related papers  (2025-07-07T08:32:29Z)
• VNJPTranslate: A comprehensive pipeline for Vietnamese-Japanese translation [0.0]
  VNJPTranslate is a pipeline designed to systematically address the Vi-Ja translation task.<n>It features a targeted data augmentation strategy using advanced LLMs with Chain-of-specifically prompting for challenging segments identified via corpus analysis.<n>We employ efficient fine-tuning techniques to create a practical and high-performing translation system.
  arXiv  Detail & Related papers  (2025-04-01T01:38:25Z)
• ViSoLex: An Open-Source Repository for Vietnamese Social Media Lexical Normalization [1.053698976085779]
  ViSoLex is an open-source system designed to address the challenges of lexical normalization for Vietnamese social media text.<n>By publishing the source code, ViSoLex aims to contribute to the development of more robust Vietnamese natural language processing tools.
  arXiv  Detail & Related papers  (2025-01-13T02:47:13Z)
• CELA: Cost-Efficient Language Model Alignment for CTR Prediction [70.65910069412944]
  Click-Through Rate (CTR) prediction holds a paramount position in recommender systems.<n>Recent efforts have sought to mitigate these challenges by integrating Pre-trained Language Models (PLMs)<n>We propose textbfCost-textbfEfficient textbfLanguage Model textbfAlignment (textbfCELA) for CTR prediction.
  arXiv  Detail & Related papers  (2024-05-17T07:43:25Z)
• Simultaneous Machine Translation with Large Language Models [51.470478122113356]
  We investigate the possibility of applying Large Language Models to SimulMT tasks. We conducted experiments using the textttLlama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
  arXiv  Detail & Related papers  (2023-09-13T04:06:47Z)
• Mobile Foundation Model as Firmware [13.225478051091763]
  sys is a collaborative management approach between the mobile OS and hardware. It amalgamates a curated selection of publicly available Large Language Models (LLMs) and facilitates dynamic data flow. It attains accuracy parity in 85% of tasks, demonstrates improved scalability in terms of storage and memory, and offers satisfactory inference speed.
  arXiv  Detail & Related papers  (2023-08-28T07:21:26Z)
• SLTUNET: A Simple Unified Model for Sign Language Translation [40.93099095994472]
  We propose a simple unified neural model designed to support multiple sign-to-gloss, gloss-to-text and sign-to-text translation tasks. Jointly modeling different tasks endows SLTUNET with the capability to explore the cross-task relatedness that could help narrow the modality gap. We show in experiments that SLTUNET achieves competitive and even state-of-the-art performance on ENIX-2014T and CSL-Daily.
  arXiv  Detail & Related papers  (2023-05-02T20:41:59Z)
• Federated Nearest Neighbor Machine Translation [66.8765098651988]
  In this paper, we propose a novel federated nearest neighbor (FedNN) machine translation framework. FedNN leverages one-round memorization-based interaction to share knowledge across different clients. Experiments show that FedNN significantly reduces computational and communication costs compared with FedAvg.
  arXiv  Detail & Related papers  (2023-02-23T18:04:07Z)
• Democratizing Neural Machine Translation with OPUS-MT [56.21988248821684]
  This paper presents the OPUS ecosystem with a focus on the development of open machine translation models and tools. We discuss our on-going mission of increasing language coverage and translation quality, and also describe on-going work on the development of modular translation models.
  arXiv  Detail & Related papers  (2022-12-04T22:16:27Z)
• Paraphrastic Representations at Scale [134.41025103489224]
  We release trained models for English, Arabic, German, French, Spanish, Russian, Turkish, and Chinese languages. We train these models on large amounts of data, achieving significantly improved performance from the original papers.
  arXiv  Detail & Related papers  (2021-04-30T16:55:28Z)
• Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders [19.44855809470709]
  Recently, universal neural machine translation (NMT) with shared encoder-decoder gained good performance on zero-shot translation. Unlike universal NMT, jointly trained language-specific encoders-decoders aim to achieve universal representation across non-shared modules. We study zero-shot translation using language-specific encoders-decoders.
  arXiv  Detail & Related papers  (2021-02-12T15:36:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.