Zhiheng Gong — accepted AI-conference papers

2026

AES: Curing Optimizer Blindness in Long-Tailed Recognition via State-Aware Correction

Fanfu Wang, Jiachang Zhan, Zhiheng Gong, Pengkun Wang, Yang Wang

ICML 2026poster

Long-tailed recognition fundamentally suffers from optimizer blindness where the optimization process mistakenly conflates the magnitude of gradient accumulation with the scarcity of semantic information. Existing strategies relying on static frequency-based priors fail to correct this bias and resu…

Cited by 0 Source ↗Scholar ↗

2025

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

Zhe Zhao, Zhiheng Gong, Pengkun Wang, HaiBin Wen, Cankun Guo, Bo Xue +4

NeurIPS 2025poster

Long-Tailed Recognition (LTR) presents a significant challenge due to extreme class imbalance, where existing methods often struggle to balance performance across head and tail classes. Directly applying multi-objective optimization (MOO) to leverage multiple LTR strategies can be complex and unstab…

Cited by 0 Source ↗Scholar ↗