Challenge: Large language models are highly advanced to user-requested tasks.
Approach: They propose a device-server hybrid inference strategy for on-device LLM customization . they construct a pool of diverse base adapters and then blend them into a customized adapter .
Outcome: The proposed method can be used on a large scale without extra training . it can be applied to large-scale LLMs without sacrificing the benefits of on-device customization.

Similar Papers

Token Level Routing Inference System for Edge Devices (2025.acl-demo)

Copied to clipboard

Challenge: Large language models (LLMs) have been gaining in performance but deployment in edge devices faces significant hurdles due to their high computational complexity.
Approach: They propose a collaborative decoding system that allows small models to perform on-device inference while selectively consulting a cloud-based large model for critical token generation.
Outcome: The proposed system achieves 60% performance gain on CommonsenseQA using a 0.5B model on an M1 MacBook, with under 7% of tokens generation uploaded to the large model in the cloud.
Personalize Your LLM: Fake it then Align it (2025.findings-naacl)

Copied to clipboard

Challenge: Existing personalization methods require fine-tuning of large language models for each user, rendering them prohibitively expensive for widespread adoption.
Approach: They propose a retrieval-based personalization approach that uses self-generated personal preference data and representation editing to enable quick and cost-effective personalization.
Outcome: The proposed approach outperforms two personalization baselines by 40% on various tasks.
A Drop-In Solution for On-the-Fly Adaptation of Speculative Decoding in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are highly memory-intensive when performing real-time inference.
Approach: They propose a technique that allows for speculative decoding to be run on the fly to maximize the efficiency of LLM inferences.
Outcome: The proposed solution can lead to 3.55-16.48% speed improvement over the standard speculative decoding, and 1.2-3.4 over the default LLMs.
Model-based Large Language Model Customization as Service (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model services require users to upload data for fine-tuning . current methods for customization are noisy and require sensitive domain data .
Approach: *Llamdex is a framework that facilitates LLM customization as a service . client uploads pre-trained domain-specific *models* rather than data .
Outcome: *Llamdex* framework improves domain-specific accuracy by up to 26% over state-of-the-art private data synthesis methods .
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM (2026.findings-acl)

Copied to clipboard

Challenge: a framework for efficient on-device inference of large language models is needed for smartphones . memory, latency, and runtime flexibility are constraints for large language model deployments.
Approach: They propose a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model for Samsung Galaxy S24 and S25 devices with SM8650 and SM8750 chipsets respectively.
Outcome: The proposed framework improves memory, latency and performance across 9 languages and 8 tasks.
Search-Adaptor: Embedding Customization for Information Retrieval (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to embed text in large language models are limited to zero-shot setups and can be integrated with any LLM.
Approach: They propose a method for customizing LLMs for information retrieval by modifying the embeddings generated by pre-trained LLM models and can be integrated with any LLM.
Outcome: The proposed method improves performance on English, multilingual, and multimodal retrieval datasets by 5% over 14 BEIR datasets.
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications.
Approach: They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases.
Outcome: The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency.
LLMs on a Budget? Say HOLA (2025.emnlp-industry)

Copied to clipboard

Challenge: Current solutions such as quantization, pruning, and Retrieval-Augmented Generation (RAG) offer only partial optimizations and often sacrifice accuracy, speed, or generality.
Approach: They propose an end-to-end optimization framework for efficient LLM deployment . it leverages Hierarchical Speculative Decoding (HSD) for faster inference without quality loss.
Outcome: HOLA delivers +17.6% EMA on GSM8K, +10.5% MCA on ARC, and reduced latency and memory on edge devices like Jetson Nano.
StitchLLM: Serving LLMs, One Block at a Time (2025.acl-long)

Copied to clipboard

Challenge: Existing techniques like distillation and pruning are not efficient for large language models.
Approach: They propose a dynamic model routing framework that uses a powerful bottom model to process all queries and a lightweight routing mechanism to allocate computational resources appropriately.
Outcome: The proposed framework improves system throughput while minimizing performance degradation.
EOP-LLM: Energy Oriented Pruning for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Inference energy consumption has grown rapidly in large language models (LLMs) but existing methods focus on reducing FLOPs or latency rather than modeling or enforcing end-to-end inference energy constraints.
Approach: They propose an energy-oriented dynamic pruning framework that enables LLM inference under explicit per-sequence energy budgets.
Outcome: EOP-LLM outperforms state-of-the-art dynamic pruning baselines while adhering to per-sequence energy constraints.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations