22 citations · 30 across the 19 of their papers we have counts for
21 papers
FluxShard: Motion-Aware Feature Cache Reuse for Collaborative Video Analytics in Mobile Edge Computing
Xiuxian Guan, Zongyuan Zhang, Zheng Lin +8
Caching and reusing intermediate features across consecutive frames is a common technique to reduce redundant computation and transmission for edge-cloud video analytics in mobile…
LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems
Tianyang Duan, Zongyuan Zhang, Zheng Lin +10
Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge de…
Sample Efficient Experience Replay in Non-stationary Environments
Tianyang Duan, Zongyuan Zhang, Songxiao Guo +8
Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (E…
LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning
Tianyang Duan, Zongyuan Zhang, Songxiao Guo +7
Multi-agent reinforcement learning (MARL) holds substantial promise for intelligent decision-making in complex environments. However, it suffers from a coordination and scalability…
RRTO: A High-Performance Transparent Offloading System for Model Inference in Mobile Edge Computing
Zekai Sun, Xiuxian Guan, Zheng Lin +8
Deploying Machine Learning (ML) applications on resource-constrained mobile devices remains challenging due to limited computational resources and poor platform compatibility. Whil…
Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing
Zekai Sun, Xiuxian Guan, Zheng Lin +8
Deploying deep neural networks (DNNs) on resource-constrained mobile devices presents significant challenges, particularly in achieving real-time performance while simultaneously c…
EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code
Yuhao Qing, Boyu Zhu, Mingzhe Du +9
Existing code generation benchmarks primarily evaluate functional correctness, with limited focus on code efficiency and often restricted to a single language like Python. To addre…
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
Zongyuan Zhang, Tianyang Duan, Zheng Lin +8
Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmenta…
State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning
Zongyuan Zhang, Tianyang Duan, Zheng Lin +7
Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitiv…
Themis: Efficient Sparse Model Training Through Fully Sharded Sparse Data Parallelism
Yuhao Qing, Guichao Zhu, Lintian Lei +9
Mixture-of-Experts (MoE) scales large language models cost-effectively, but expert-parallel training suffers severe straggler effects from skewed expert loads. Current systems freq…
Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
Tianyang Duan, Zongyuan Zhang, Zheng Lin +7
Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for eva…
EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
Dong Huang, Guangtao Zeng, Jianbo Dai +6
As large language models (LLMs) play an increasingly important role in code generation, enhancing both correctness and efficiency has become crucial. Current methods primarily focu…
Measuring the Influence of Incorrect Code on Test Generation
Dong Huang, Jie M. Zhang, Mark Harman +2
It is natural to suppose that a Large Language Model is more likely to generate correct test cases when prompted with correct code under test, compared to incorrect code under test…
OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Model
Junming Wang, Xiuxian Guan, Zekai Sun +4
Air-ground robots (AGRs) are widely used in surveillance and disaster response due to their exceptional mobility and versatility (i.e., flying and driving). Current AGR navigation…
Learning Manipulation by Predicting Interaction
Jia Zeng, Qingwen Bu, Bangjun Wang +12
Representation learning approaches for robotic manipulation have boomed in recent years. Due to the scarcity of in-domain robot data, prevailing methodologies tend to leverage larg…
Hybrid-Parallel: Achieving High Performance and Energy Efficient Distributed Inference on Robots
Zekai Sun, Xiuxian Guan, Junming Wang +6
The rapid advancements in machine learning techniques have led to significant achievements in various real-world robotic tasks. These tasks heavily rely on fast and energy-efficien…
EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization
Dong Huang, Jianbo Dai, Han Weng +5
Large language models (LLMs) have shown remarkable progress in code generation, but their generated code often suffers from inefficiency, resulting in longer execution times and hi…
Themis: Automatic and Efficient Deep Learning System Testing with Strong Fault Detection Capability
Dong Huang, Tsz On Li, Xiaofei Xie +1
Deep Learning Systems (DLSs) have been widely applied in safety-critical tasks such as autopilot. However, when a perturbed input is fed into a DLS for inference, the DLS often has…
AGRNav: Efficient and Energy-Saving Autonomous Navigation for Air-Ground Robots in Occlusion-Prone Environments
Junming Wang, Zekai Sun, Xiuxian Guan +6
The exceptional mobility and long endurance of air-ground robots are raising interest in their usage to navigate complex environments (e.g., forests and large buildings). However,…
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
Dong Huang, Yuhao Qing, Weiyi Shang +2
Code generation models have increasingly become integral to aiding software development. Although current research has thoroughly examined the correctness of the code produced by c…
AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
Dong Huang, Jie M. Zhang, Michael Luck +3
The advancement of natural language processing (NLP) has been significantly boosted by the development of transformer-based large language models (LLMs). These models have revoluti…