Xinghao Chen

Researcher, Huawei Noah's Ark Lab

Joined

July 2019

Names

Xinghao Chen

Emails

****@outlook.com (Confirmed)

****@huawei.com (Confirmed)

****@mails.tsinghua.edu.cn (Confirmed)

Personal Links

Google Scholar

DBLP

ORCID

Career & Education History

Researcher

Huawei Noah's Ark Lab (huawei.com)

2019 – Present

PhD student

Tsinghua University (tsinghua.edu.cn)

2013 – 2019

Advisors, Relations & Conflicts

Coauthor

Yunhe Wang

Present

Expertise

Deep Learning

2013 – Present

Computer Vision

2013 – Present

Publications

AutoLoss-GMS: Searching Generalized Margin-based Softmax Loss Function for Person Re-identification
Hongyang Gu, Jianmin Li, Guangyuan Fu, Chifong Wong, Xinghao Chen, Jun Zhu
- CVPR 2022
- Readers: Everyone
Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting
Zhen-Liang Ni, Xiaowen Ma, Zhenkai Wu, Shuai Xiao, Han Shu, Xinghao Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
OmniEval: A Benchmark for Evaluating Omni-modal Models with Visual, Auditory, and Textual Inputs
Yiman Zhang, Ziheng Luo, Qiangyu YAN, Wei He, Borui Jiang, Xinghao Chen, Kai Han
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models
Mouxiao Huang, Borui Jiang, Dehua Zheng, Hailin Hu, Kai Han, Xinghao Chen
- ICLR 2026 Poster
- Readers: Everyone
RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration
Yan CHEN, Yi Wen, Wei Li, Junchao Liu, Yong Guo, Jie Hu, Xinghao Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
An Empirical Study of Extremely Low-Bit Quantization for Large Language Models
Yuanyuan Xi, Zhijun Tu, Jian Li, Hanting Chen, Kai Han, Erkang Bo, Jie Hu, Xinghao Chen
- Submitted to ICLR 2026
- Readers: Everyone
Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking
Dengming Zhang, Xiaowen Ma, Zhen-Liang Ni, Zhenkai Wu, Han Shu, Xin Jiang, Xinghao Chen
- ICLR 2026 Poster
- Readers: Everyone
Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing
Zhentao Zou, Zhengrong Yue, Kunpeng Du, Binglei Bao, Hanting Li, Haizhen Xie, Guozheng Xu, Yue Zhou, Yali Wang, Jie Hu, Xue Jiang, Xinghao Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
Qianhan Feng, Wenshuo Li, Tong Lin, Xinghao Chen
- OpenReview Archive Direct Upload
- Readers: Everyone
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement
Qianhan Feng, Wenshuo Li, Tong Lin, Xinghao Chen
- CVPR 2025
- Readers: Everyone

View all 55 publications

Co-Authors

View all 117 co-authors