Risultati della ricerca - Han, Haochen

A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels di Han, Haochen, Luo, Minnan, Liu, Huan, Nan, Fang

Testo

Unlearning the Noisy Correspondence Makes CLIP More Robust di Han, Haochen, Wang, Alex Jinpeng, Ye, Peijun, Liu, Fangming

Testo

Negation-Aware Test-Time Adaptation for Vision-Language Models di Han, Haochen, Wang, Alex Jinpeng, Liu, Fangming, Zhu, Jun

Testo

Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval di Han, Haochen, Zheng, Qinghua, Dai, Guang, Luo, Minnan, Wang, Jingdong

Testo

Noise-Tolerant Learning for Audio-Visual Action Recognition di Han, Haochen, Zheng, Qinghua, Luo, Minnan, Miao, Kaiyao, Tian, Feng, Chen, Yan

Testo

TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering di Gui, Rui, Wan, Yang, Han, Haochen, Mao, Dongxing, Liu, Fangming, Li, Min, Wang, Alex Jinpeng

Testo

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT di Dong, Zhuobai, Yi, Junchao, Zheng, Ziyuan, Han, Haochen, Zheng, Xiangxi, Wang, Alex Jinpeng, Liu, Fangming, Li, Linjie

Testo

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models di Hou, Jiacheng, Sun, Yining, Jin, Ruochong, Han, Haochen, Liu, Fangming, Chan, Wai Kin Victor, Wang, Alex Jinpeng

Testo

Disentangled Noisy Correspondence Learning di Dang, Zhuohang, Luo, Minnan, Wang, Jihong, Jia, Chengyou, Han, Haochen, Wan, Herun, Dai, Guang, Chang, Xiaojun, Wang, Jingdong

Testo

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging di Wang, Bowen, Wan, Haiyuan, Shi, Liwen, Yang, Chen, He, Peng, Ma, Yue, Han, Haochen, Li, Wenhao, Tan, Tiao, Li, Yongjian, Liu, Fangming, Gong, Yifan, Zhang, Sheng

Testo