Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference (2024.acl-long)
Copied to clipboard
| 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
Sravanth Kodavanti, Sowmya Vajrala, Srinivas Soumitri Miriyala, Utsav Tiwari, Uttam Kumar, Utkarsh Kumar Mahawar, Achal Pratap Singh, Arya D, Narendra Mutyala, Vikram Nelvoy Rajendiran, Sharan Kumar Allur, Euntaik Lee, Dohyoung Kim, HyeonSu Lee, Gyusung Cho, JungBae Kim
| 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
Kayhan Behdin, Ata Fatahibaarzi, Qingquan Song, Yun Dai, Aman Gupta, Zhipeng Wang, Hejian Sang, Shao Tang, Gregory Dexter, Sirou Zhu, Siyu Zhu, Tejas Dharamsi, Vignesh Kothapalli, Zhoutong Fu, Yihan Cao, Pin-Lun Hsu, Fedor Borisyuk, Natesh S. Pillai, Luke Simon, Rahul Mazumder
| 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
Zohaib Hasan Siddiqui, Jiechao Gao, Ebad Shabbir, Mohammad Anas Azeez, Rafiq Ali, Gautam Siddharth Kashyap, Usman Naseem
| 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
Bodun Hu, Shuozhe Li, Saurabh Agarwal, Myungjin Lee, Akshay Jajoo, Jiamin Li, Le Xu, Geon-Woo Kim, Donghyun Kim, Hong Xu, Amy Zhang, Aditya Akella
| 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. |