mlsanityData to 7 Oct 2026

HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization

arXiv 2604.14159 ↗First posted 23 Mar 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce personalized text. While lightweight large language models (LLMs) make on-device auxiliary generation feasible, enabling deeply personalized, privacy-preserving, and real-time generative IMEs poses fundamental challenges.To this end, we present HUOZIIME, a personalized on-device IME powered by LLM. We endow HUOZIIME with initial human-like prediction ability by post-training a base LLM on synthesized personalization data. Notably, a hierarchical memory mechanism is designed to continually capture and leverage user-specific input history. Furthermore, we perform systemic optimizations tailored to on-device LLMbased IME deployment, ensuring efficient and responsive operation under mobile constraints.Experiments demonstrate efficient on-device execution and high-fidelity memory-driven personalization. Code and package are available at https://github.com/Shan-HIT/HuoziIME.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 23 Mar 2026.

Builds on

14 of 27 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  5. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  8. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  9. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  10. 2023Prompt Cache: Modular Attention Reuse for Low-Latency Inferencecited by 255
  11. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 211
  12. 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reusecited by 60
2 more
  1. 2024CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMscited by 7
  2. 2025CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysiscited by 5

Built on by

Not cited yet.