30 citations · 62 across the 19 of their papers we have counts for
20 papers
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
Feng Luo, Yu-Neng Chuang, Guanchu Wang +8
Reasoning-capable large language models (LLMs) achieve strong performance on complex tasks but often exhibit overthinking after distillation, generating unnecessarily long chain-of…
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Yang Sui, Yu-Neng Chuang, Guanchu Wang +9
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, ha…
Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
Xuansheng Wu, Jiayi Yuan, Wenlin Yao +2
Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for…
The Science of Evaluating Foundation Models
Jiayi Yuan, Jiamu Zhang, Andrew Wen +1
The emergent phenomena of large foundation models have revolutionized natural language processing. However, evaluating these models presents significant challenges due to their siz…
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang +8
Ensuring the security of released large language models (LLMs) poses a significant dilemma, as existing mechanisms either compromise ownership rights or raise data privacy concerns…
DHP Benchmark: Are LLMs Good NLG Evaluators?
Yicheng Wang, Jiayi Yuan, Yu-Neng Chuang +7
Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks; this is often referred to as ``LLM-as-a-judge'' paradigm. However, t…
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
Jiayi Yuan, Hongyi Liu, Shaochen Zhong +9
Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts. This capability enables complex task-…
LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting
Yu-Neng Chuang, Songchen Li, Jiayi Yuan +11
Time Series Forecasting (TSF) has long been a challenge in time series analysis. Inspired by the success of Large Language Models (LLMs), researchers are now developing Large Time…
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
Hongyi Liu, Shaochen Zhong, Xintong Sun +12
Finetuning LLMs with LoRA has gained significant popularity due to its simplicity and effectiveness. Often, users may even find pluggable, community-shared LoRAs to enhance their b…
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Zirui Liu, Jiayi Yuan, Hongye Jin +5
Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key…
Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots
Ruixiang Tang, Jiayi Yuan, Yiming Li +3
In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susc…
Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke
Qizhang Feng, Jiayi Yuan, Forhan Bin Emdad +3
Stroke is a significant cause of mortality and morbidity, necessitating early predictive strategies to minimize risks. Traditional methods for evaluating patients, such as Acute Ph…
NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants
Zhongzhi Yu, Yonggan Fu, Jiayi Yuan +2
Tiny deep learning has attracted increasing attention driven by the substantial demand for deploying deep learning on numerous intelligent Internet-of-Things devices. However, it i…
Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design
Yonggan Fu, Zhifan Ye, Jiayi Yuan +4
Novel view synthesis is an essential functionality for enabling immersive experiences in various Augmented- and Virtual-Reality (AR/VR) applications, for which generalizable Neural…
Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning
Yonggan Fu, Ye Yuan, Shang Wu +2
Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks. Ho…
Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint
Chia-Yuan Chang, Jiayi Yuan, Sirui Ding +5
Clinical trials are indispensable in developing new treatments, but they face obstacles in patient recruitment and retention, hindering the enrollment of necessary participants. To…
Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching
Jiayi Yuan, Ruixiang Tang, Xiaoqian Jiang +1
The process of matching patients with suitable clinical trials is essential for advancing medical research and providing optimal care. However, current approaches face challenges s…
ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement
Chaojian Li, Wenwan Chen, Jiayi Yuan +2
Social ambiance describes the context in which social interactions happen, and can be measured using speech audio by counting the number of concurrent speakers. This measurement ha…
EyeCoD: Eye Tracking System Acceleration via FlatCam-based Algorithm & Accelerator Co-Design
Haoran You, Cheng Wan, Yang Zhao +11
Eye tracking has become an essential human-machine interaction modality for providing immersive experience in numerous virtual and augmented reality (VR/AR) applications desiring h…
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
Yonggan Fu, Haichuan Yang, Jiayi Yuan +5
Efficient deep neural network (DNN) models equipped with compact operators (e.g., depthwise convolutions) have shown great potential in reducing DNNs' theoretical complexity (e.g.,…