collaborators

6 papers

cs.LG2026

Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs

Jinyi Liu, Wei Chen, Pengyu Chen +4

The paper introduces Prox, a training-free framework that sparsifies feed‑forward network activations in large language models by approximating intermediate‑channel salience, enabl…

cs.NE2025

An LLM-Empowered Adaptive Evolutionary Algorithm For Multi-Component Deep Learning Systems

Haoxiang Tian, Xingshuo Han, Guoquan Wu +5

Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep…

cs.SE2025

Temac: Multi-Agent Collaboration for Automated Web GUI Testing

Chenxu Liu, Zhiyu Gu, Guoquan Wu +3

Quality assurance of web applications is critical, as web applications play an essential role in people's daily lives. To reduce labor costs, automated web GUI testing (AWGT) is wi…

cs.SE2025

Deep Reinforcement Learning for Automated Web GUI Testing

Zhiyu Gu, Chenxu Liu, Guoquan Wu +5

Automated GUI testing of web applications has always been considered a challenging task considering their large state space and complex interaction logic. Deep Reinforcement Learni…

cs.RO2025

Testing the Fault-Tolerance of Multi-Sensor Fusion Perception in Autonomous Driving Systems

Haoxiang Tian, Wenqiang Ding, Xingshuo Han +5

High-level Autonomous Driving Systems (ADSs), such as Google Waymo and Baidu Apollo, typically rely on multi-sensor fusion (MSF) based approaches to perceive their surroundings. Th…

cs.SE2025

LMM-enhanced Safety-Critical Scenario Generation for Autonomous Driving System Testing From Non-Accident Traffic Videos

Haoxiang Tian, Xingshuo Han, Yuan Zhou +6

Safety testing serves as the fundamental pillar for the development of autonomous driving systems (ADSs). To ensure the safety of ADSs, it is paramount to generate a diverse range…