In 2021, I earned my master’s degree from Hebei University of Science and Technology. During 2018 to 2020, I had the opportunity to conduct research as a visiting student at Tsinghua University under the mentorship of Professor Hua Xu. My research interests include multimodal representation learning, vision-language pretraining, and contrastive learning.

I’m actively hiring interns in the fields of multimodal representation learning, large-scale data cleaning, RAG, and Agent. If you want to collaborate with me, please feel free to contact me😊.

Email:kaichengyang0828@gmail.com; kaichengyang@deepglint.com.

Google Scholar and Citation Map.

🔥 News

• 2025.02: We present the RealSyn Dataset.
• 2024.12: 🎉 CLIP-CID has been accepted by AAAI2025.
• 2024.11: 🎉 ORID has been accepted by WACV2025(Oral).
• 2024.10: We present the Croc.
• 2024.09: 🎉 RWKV-CLIP has been accepted by EMNLP2024(Main).
• 2024.07: 🎉 MLCD has been accepted by ECCV2024.
• 2024.06: We present the High-Fidelity Facial Albedo.
• 2024.04: Our team achieve 1st Place on the 1st SkatingVerse Challenge(18th IEEE International Conference on Automatic Face and Gesture Recognition workshop).
• 2024.03: 🎉 LaPA has been accepted by CVPRW2024.
• 2023.09: I will attend ICCV2023, happy to see you in ICCV (Paris) in person.
• 2023.09: 🎉 Our team achieve co-winner in OpenFAD Challenge(ICCV2023 workshop).
• 2023.07: 🎉 ALIP has been accepted by ICCV2023.
• 2023.05: I will attend ICLR2023, happy to see you in ICLR (Kigali) in person.
• 2023.01: 🎉 Unicom has been accepted by ICLR2023.
• 2022.10: We achieve 11/1022(top 1%) in the Google Universal Image Embedding Challenge(ECCV2022 Instance-Level Recognition workshop).
• 2022.07: I joined DeepGlint as an algorithm researcher.
• 2021.01: I joined MovieBook as an algorithm engineer.
• 2020.10: 🎉 CM-BERT has been accepted by ACM MM2020(Oral).
• 2020.07: 🎉 CH-SIMS has been accepted by ACL2020.

💻 Public Papers

AAAI2025

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination
Kaicheng Yang*, Tiancheng Gu*, Xiang An, Haiqiang Jiang, Xiangzi Dai, Ziyong Feng, Weidong Cai, Jiankang Deng (First author)

Arxiv

WACV2025

ORID: Organ-Regional Information Driven Framework for Radiology Report Generation
Tiancheng Gu*, Kaicheng Yang*, Xiang An, Ziyong Feng, Dongnan Liu, Weidong Cai (Oral, Equal First author)

Arxiv

EMNLP2024

RWKV-CLIP: A Robust Vision-Language Representation Learner
Tiancheng Gu*, Kaicheng Yang*, Xiang An, Ziyong Feng, Dongnan Liu, Weidong Cai, Jiankang Deng (Equal First author)

Arxiv, Code

ECCV2024

Multi-label Cluster Discrimination for Visual Representation Learning
Xiang An, Kaicheng Yang, Xiangzi Dai, Ziyong Feng, Jiankang Deng

Arxiv, Code

CVPRW2024

LaPA: Latent Prompt Assist Model For Medical Visual Question Answering
Tiancheng Gu, Kaicheng Yang, Dongnan Liu, Weidong Cai

Arxiv, Code

ICCV2023

ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
Kaicheng Yang, Jiankang Deng, Xiang An, Jiawei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

Arxiv, Code

ICLR2023

Unicom: Universal and Compact Representation Learning for Image Retrieval
Xiang An, Jiankang Deng, Kaicheng Yang, Jiawei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

Arxiv, Code

ACM MM2020

CM-BERT: Cross-Modal BERT for Text-Audio Sentiment Analysis
Kaicheng Yang, Hua Xu, Kai Gao (Oral)

Code

ACL2020

CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotations of Modality
Wenmeng Yu, Hua Xu, Fanyang Meng, Yilin Zhu, Yixiao Ma, Jiele Wu, Jiyun Zou, Kaicheng Yang

Code

🧑‍🏫Professional Services

• Conferences: ECCV, CVPR, ICCV, ACL, EMNLP, NAACL, ACM MM
• Journals: ESWA

📖 Educations

• 2019.01 - 2021.01, Visting Postgraduate Student, Tsinghua University, Beijing.
• 2018.09 - 2021.01, Master, Hebei University of Science and Technology, Shijiazhuang.
• 2012.09 - 2015.06, Undergraduate, Hebei University of Science and Technology, Shijiazhuang.

💻 Work Experience

• 2022.07 - Now, DeepGlint, Beijing.
• 2021.01 - 2022.06, Moviebook, Beijing.