2 citations · 5 across the 10 of their papers we have counts for
13 papers
Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation
Dancheng Liu, Amir Nassereldine, Chenhui Xu +1
Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this wor…
FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
Chenhui Xu, Dancheng Liu, Amir Nassereldine +1
Physics Informed Neural Networks (PINNs) often exhibit failure modes in which the PDE residual loss converges while the solution error stays large, a phenomenon traditionally blame…
Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability
Chenhui Xu, Dancheng Liu, Jiajie Li +3
Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving per…
Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
Yuting Hu, Chenhui Xu, Ruiyang Qin +4
Partial perception deficits can compromise autonomous vehicle safety by disrupting environmental understanding. Existing protocols typically default to entirely risk-avoidant actio…
NVCiM-PT: An NVCiM-assisted Prompt Tuning Framework for Edge LLMs
Ruiyang Qin, Pengyu Ren, Zheyu Yan +7
Large Language Models (LLMs) deployed on edge devices, known as edge LLMs, need to continuously fine-tune their model parameters from user-generated data under limited resource con…
Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
Dancheng Liu, Jason Yang, Ishan Albrecht-Buehler +5
Speech is a fundamental aspect of human life, crucial not only for communication but also for cognitive, social, and academic development. Children with speech disorders (SD) face…
Large Language Models have Intrinsic Self-Correction Ability
Dancheng Liu, Amir Nassereldine, Ziming Yang +8
Large language models (LLMs) have attracted significant attention for their exceptional abilities in various natural language processing tasks, but they suffer from hallucinations…
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…
Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble
Dancheng Liu, Chenhui Xu, Jiajie Li +2
For collaborative inference through a cloud computing platform, it is sometimes essential for the client to shield its sensitive information from the cloud provider. In this paper,…
Predicting the Performance-Cost Trade-off of Applications Across Multiple Systems
Amir Nassereldine, Safaa Diab, Mohammed Baydoun +4
In modern computing environments, users may have multiple systems accessible to them such as local clusters, private clouds, or public clouds. This abundance of choices makes it di…
Excel Spreadsheet Analyzer
Amir Nassereldine, Patrick Chen, Jinjun Xiong
Spreadsheets are widely used in various fields to do large numerical analysis. While several companies have relied on spreadsheets for decades, data scientists are going in the dir…
A Framework for High-throughput Sequence Alignment using Real Processing-in-Memory Systems
Safaa Diab, Amir Nassereldine, Mohammed Alser +3
Sequence alignment is a memory bound computation whose performance in modern systems is limited by the memory bandwidth bottleneck. Processing-in-memory architectures alleviate thi…
High-throughput Pairwise Alignment with the Wavefront Algorithm using Processing-in-Memory
Safaa Diab, Amir Nassereldine, Mohammed Alser +3
We show that the wavefront algorithm can achieve higher pairwise read alignment throughput on a UPMEM PIM system than on a server-grade multi-threaded CPU system.