An Empirical Study of On-Device Translation for Real-Time Live-Stream Chat on Mobile Devices

arXiv:2601.02641 · cs.AI · Submitted 2026-01-06 · Read on arXiv

cs.AI

Submitted: 2026-01-06

Updated: 2026-10-04

Comments: AACL-IJCNLP 2026 Main Track

Code: https://github.com/mybigday/llama.rn

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes

Sources

• SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
• LLMs in Mobile Apps: Practices, Challenges, and Opportunities
• MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
• DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization
• Gemma 3 Technical Report
• No Language Left Behind: Scaling Human-Centered Machine Translation
• On-Device Language Models: A Comprehensive Review
• Qwen3 Technical Report
• MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems