Zhangyu He — accepted AI-conference papers

2026

Beyond Logits: Coherent Hallucination Mitigation via Attention Contrastive Decoding

Yujia Chen, Rui Sun, Wangkai Li, Huayu Mai, Bingzhou Wang, Zhangyu He +3

ICML 2026poster

Large Vision-Language Models (LVLMs) demonstrate impressive multimodal capabilities, yet suffer from hallucination—generating factually inaccurate content. Contrastive Decoding (CD) mitigates this by contrasting amateur and expert branches at the logit level. However, our investigation reveals that …

Cited by 0 Source ↗Scholar ↗

2026

From Softmax to Dirichlet: Evidential Learning for Semi-supervised Semantic Segmentation

Huayu Mai, Rui Sun, Yujia Chen, Wangkai Li, Bingzhou Wang, Aibing Li +2

CVPR 2026

The critical challenge of semi-supervised semantic segmentation lies in how to fully exploit a large volume of unlabeled data to improve the model's generalization performance for robust segmentation. However, existing softmax scores-based filtering methods tend to be affected by the overconfidence

Cited by 0 Source ↗Scholar ↗