4 citations · 11 across the 17 of their papers we have counts for
19 papers
Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity
Tuowei Wang, Kun Li, Zixu Hao +5
The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter…
LLM-Driven Self-Refinement for Embodied Drone Task Planning
Deyu Zhang, Xicheng Zhang, Jiahao Li +6
We introduce SRDrone, a novel system designed for self-refinement task planning in industrial-grade embodied drones. SRDrone incorporates two key technical contributions: First, it…
Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval
Deyu Zhang, Tingting Long, Jinrui Zhang +3
Enabling efficient text-video retrieval on edge-end devices is critical for real-world applications. Yet, existing methods face a critical challenge in balancing accuracy and compu…
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
Ziqing Qiao, Yongheng Deng, Jiali Zeng +7
Large Reasoning Models (LRMs) perform strongly in complex reasoning tasks via Chain-of-Thought (CoT) prompting, but often suffer from verbose outputs, increasing computational over…
AugFL: Augmenting Federated Learning with Pretrained Models
Sheng Yue, Zerui Qin, Yongheng Deng +3
Federated Learning (FL) has garnered widespread interest in recent years. However, owing to strict privacy policies or limited storage capacities of training participants such as I…
LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning
Tuowei Wang, Xingyu Chen, Kun Li +3
The escalating demand for long-context applications has intensified the necessity of extending the LLM context windows. Despite recent fine-tuning approaches successfully expanding…
Enabling Cardiac Monitoring using In-ear Ballistocardiogram on COTS Wireless Earbuds
Yongjian Fu, Ke Sun, Ruyao Wang +4
The human ear offers a unique opportunity for cardiac monitoring due to its physiological and practical advantages. However, existing earable solutions require additional hardware…
Matryoshka: Optimization of Dynamic Diverse Quantum Chemistry Systems via Elastic Parallelism Transformation
Tuowei Wang, Kun Li, Donglin Bai +6
AI infrastructures, predominantly GPUs, have delivered remarkable performance gains for deep learning. Conversely, scientific computing, exemplified by quantum chemistry systems, s…
MobiFuse: A High-Precision On-device Depth Perception System with Multi-Data Fusion
Jinrui Zhang, Deyu Zhang, Tingting Long +6
We present MobiFuse, a high-precision depth perception system on mobile devices that combines dual RGB and Time-of-Flight (ToF) cameras. To achieve this, we leverage physical princ…
ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries
Wangyu Xue, Chen Qian, Jiayi Wu +5
Existing works on human-centric video understanding typically focus on analyzing specific moment or entire videos. However, many applications require higher precision at the frame…
EdgeOAR: Real-time Online Action Recognition On Edge Devices
Wei Luo, Deyu Zhang, Ying Tang +2
This paper addresses the challenges of Online Action Recognition (OAR), a framework that involves instantaneous analysis and classification of behaviors in video streams. OAR must…
Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
Tuowei Wang, Ruwen Fan, Minxing Huang +6
Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive compu…
OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
Sheng Yue, Xingyuan Hua, Ju Ren +3
In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal enviro…
How to Leverage Diverse Demonstrations in Offline Imitation Learning
Sheng Yue, Jiani Liu, Xingyuan Hua +4
Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental probl…
You Can Use But Cannot Recognize: Preserving Visual Privacy in Deep Neural Networks
Qiushi Li, Yan Zhang, Ju Ren +2
Image data have been extensively used in Deep Neural Network (DNN) tasks in various scenarios, e.g., autonomous driving and medical image analysis, which incurs significant privacy…
RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
Yang Xu, Yunlin Tan, Cheng Zhang +6
Embedding watermarks into models has been widely used to protect model ownership in federated learning (FL). However, existing methods are inadequate for protecting the ownership o…
Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer
Yongheng Deng, Ziqing Qiao, Ju Ren +2
While large language models (LLMs) are empowered with broad knowledge, their task-specific performance is often suboptimal. It necessitates fine-tuning LLMs with task-specific data…
SYSFLOW: Efficient Execution Platform for IoT Devices
Jun Lu, Zhenya Ma, Yinggang Gao +2
Traditional executable delivery models pose challenges for IoT devices with limited storage, necessitating the download of complete executables and dependencies. Network solutions…
TODG: Distributed Task Offloading with Delay Guarantees for Edge Computing
Sheng Yue, Ju Ren, Nan Qiao +4
Edge computing has been an efficient way to provide prompt and near-data computing services for resource-and-delay sensitive IoT applications via computation offloading. Effective…