Hongyi Cai

According to our database, Hongyi Cai authored at least 26 papers between 2011 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Once-For-All: A Train-Once and Select-Anytime Framework for Multimodal Instruction Tuning.

Mingkang Dong, Hongyi Cai, Xiwen Lei, Jie Li, Tao Zhang, Muxin Pu

CoRR, May, 2026

Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model.

Tao Lin, Yuxin Du, Jiting Liu, Nuobei Zhu, Yunhe Li, Yuqian Fu, Yinxinyu Chen, Hongyi Cai, Zewei Ye, Bing Cheng, Kai Ye, Yiran Mao, Yilei Zhong, MingKang Dong, Junchi Yan, Gen Li, Bo Zhao

CoRR, May, 2026

VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning.

Mingkang Dong, Hongyi Cai, Jie Li, Sifan Zhou, Bin Ren, Kunyu Peng, Yuqian Fu

CoRR, March, 2026

When Vision Meets Texts in Listwise Reranking.

Hongyi Cai

CoRR, January, 2026

Cross-modal local and global alignment for Chinese Character Recognition.

Junjie Yang, Anna Zhu, Hongyi Cai

Pattern Recognit., 2026

2025

Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks.

Jie Li, Hongyi Cai, Mingkang Dong, Muxin Pu, Shan You, Fei Wang, Tao Huang

CoRR, November, 2025

VLA-Pruner: Temporal-Aware Dual-Level Visual Token Pruning for Efficient Vision-Language-Action Inference.

Ziyan Liu, Yeqiu Chen, Hongyi Cai, Tao Lin, Shuo Yang, Zheng Liu, Bo Zhao

CoRR, November, 2025

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment.

Tao Lin, Yilei Zhong, Yuxin Du, Jingjing Zhang, Jiting Liu, Yinxinyu Chen, Encheng Gu, Ziyan Liu, Hongyi Cai, Yanwen Zou, Lixing Zou, Zhaoye Zhou, Gen Li, Bo Zhao

CoRR, November, 2025

A Vision for Access Control in LLM-based Agent Systems.

Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, XiaoFeng Wang, Yang Liu

CoRR, October, 2025

AutoDebias: Automated Framework for Debiasing Text-to-Image Models.

Hongyi Cai, Mohammad Mahdinur Rahman, Mingkang Dong, Jie Li, Muxin Pu, Zhili Fang, Yinan Peng, Hanjun Luo, Yang Liu

CoRR, August, 2025

MergeIT: From Selection to Merging for Efficient Instruction Tuning.

Hongyi Cai, Yuqian Fu, Hongming Fu, Bo Zhao

CoRR, March, 2025

CFPFormer: Cross Feature-Pyramid Transformer Decoder for Medical Image Segmentation.

Hongyi Cai, Mohammad Mahdinur Rahman, Wenzhen Dong, Jingyu Wu

Proceedings of the International Joint Conference on Neural Networks, 2025

To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts.

Yukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Agent Behavior: The Regulatory Object of the Agent-Centric Online Ecosystem in Digital Age.

Qiang Zhang, Pei Yan, Yijia Xu, Xinfeng Li, Hongyi Cai, Chuanpo Fu, Yong Fang, Yang Liu

Proceedings of the Engineering of Complex Computer Systems - 29th International Conference, 2025

A Vision for Access Control in LLM Agent Systems.

Dong Huang, Jie Li, Hongyi Cai, Xinfeng Li, Yijia Xu, Wenbin Tang, Jie Zhang, Yang Liu

Proceedings of the Engineering of Complex Computer Systems - 29th International Conference, 2025

How Effective is In-Context Learning with Large Language Models for Rare Cell Identification in Single-Cell Expression Data?

Huaiyuan Yao, Zhenxiao Cao, Zhongman Wang, Xiewei Ni, Jinyan Dong, Hongyi Cai, Yuqiang Han, Xiao Luo

Proceedings of the IEEE International Conference on Data Mining, 2025

AgileIR: Memory-Efficient Group Shifted Windows Attention for Lightweight Image Restoration.

Hongyi Cai, Mohammad Mahdinur Rahman, Jingyu Wu, Wenzhen Dong, Jie Li

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2025, 2025

Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning.

Hongyi Cai, Jie Li, Mohammad Mahdinur Rahman, Wenzhen Dong

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

Enhancing Large Language Models' Situated Faithfulness to External Contexts.

Yukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra

CoRR, 2024

AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration.

Hongyi Cai, Mohammad Mahdinur Rahman, Mohammad Shahid Akhtar, Jie Li, Jingyu Wu, Zhili Fang

CoRR, 2024

CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection.

Hongyi Cai, Mohammad Mahdinur Rahman, Jingyu Wu, Yulun Deng

CoRR, 2024

AccidentBlip2: Accident Detection With Multi-View MotionBlip2.

Yihua Shao, Hongyi Cai, Xinwei Long, Weiyi Lang, Zhe Wang, Haoran Wu, Yan Wang, Jiayi Yin, Yang Yang, Yisheng Lv, Zhen Lei

CoRR, 2024

Cross-Modal Alignment of Local and Global Features for Zero-Shot Chinese Character Recognition.

Hongyi Cai, Anna Zhu

Proceedings of the IEEE International Conference on Image Processing, 2024

2023

An Adaptive Gradient Privacy-Preserving Algorithm for Federated XGBoost.

Hongyi Cai, Jianping Cai, Lan Sun

Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning, 2023

2020

Improving High Dynamic Range Image Based Light Measurement.

Hankun Li, Hongyi Cai, Guanghui Wang

Proceedings of the 2020 IEEE International Conference on Systems, Man, and Cybernetics, 2020

2011

A Camera-Aided Legibility Assessment Protocol of Displays for Enhanced Human-Computer Interaction.

Hongyi Cai

Proceedings of the Design, User Experience, and Usability. Theory, Methods, Tools and Practice, 2011