Qiong Gu — accepted AI-conference papers

2026

Breaking Multi-Task Curse: Reward-Weighted Evolution for Black-Box Many-Task Optimization

Yanchi Li, Jiao Liu, Wenyin Gong, Qiong Gu, Yue Zhao, Yew Soon ONG

ICML 2026poster

Evolutionary multi-tasking accelerates black-box optimization via knowledge transfer but falters in scenarios involving many low-similarity tasks. We identify this scalability barrier as the *Multi-Task Curse*, driven by evaluation budget dispersion and negative transfer. To overcome this, we propos…

Cited by 0 Source ↗Scholar ↗

2024

CountFormer: Multi-View Crowd Counting Transformer

Hong Mo*, Xiong Zhang*, Jianchao Tan, Cheng Yang, Qiong Gu, Bo Hang +1

ECCV 2024poster

"Multi-view counting (MVC) methods have shown their superiority over single-view counterparts, particularly in situations characterized by heavy occlusion and severe perspective distortions. However, hand-crafted heuristic features and identical camera layout requirements in conventional MVC methods…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗