activity
20222026
most citedHybrid Gate-Pulse Model for Variational Quantum Algorithms

2 citations · 3 across the 4 of their papers we have counts for

collaborators

7 papers

cs.LG2026

Multilingual Safety Alignment via Self-Distillation

Ruiyang Qin, Qingzhuo Wang, Dongrui Liu +3

Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak at…

cs.SD2024

Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge

Ruiyang Qin, Dancheng Liu, Gelei Xu +7

The combination of Large Language Models (LLM) and Automatic Speech Recognition (ASR), when deployed on edge devices (called edge ASR-LLM), can serve as a powerful personalized ass…

cs.CV2024

An Adaptive System for Wearable Devices to Detect Stress Using Physiological Signals

Gelei Xu, Ruiyang Qin, Zhi Zheng +1

Timely stress detection is crucial for protecting vulnerable groups from long-term detrimental effects by enabling early intervention. Wearable devices, by collecting real-time phy…

cs.CL2024

PI-Whisper: Designing an Adaptive and Incremental Automatic Speech Recognition System for Edge Devices

Amir Nassereldine, Dancheng Liu, Chenhui Xu +3

Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained A…

cs.LG2024

Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices

Ruiyang Qin, Dancheng Liu, Chenhui Xu +9

The scaling laws have become the de facto guidelines for designing large language models (LLMs), but they were studied under the assumption of unlimited computing resources for bot…

cs.LG20241 cited

Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures

Ruiyang Qin, Zheyu Yan, Dewen Zeng +8

Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized…