Hongyi Cai

23 papers A* 2B 5Journal 12Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning.
CoRR
Mingkang Dong, Hongyi Cai, Jie Li, Sifan Zhou, Bin Ren, Kunyu Peng, Yuqian Fu
2026 J jnl
When Vision Meets Texts in Listwise Reranking.
CoRR
Hongyi Cai
2025 B conf
A Vision for Access Control in LLM Agent Systems.
ICECCS
Dong Huang, Jie Li, Hongyi Cai, Xinfeng Li, Yijia Xu, Wenbin Tang, Jie Zhang, Yang Liu
2025 J jnl
A Vision for Access Control in LLM-based Agent Systems.
CoRR
Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, Xiaofeng Wang, Yang Liu
2025 B conf
Agent Behavior: The Regulatory Object of the Agent-Centric Online Ecosystem in Digital Age.
ICECCS
Qiang Zhang, Pei Yan, Yijia Xu, Xinfeng Li, Hongyi Cai, Chuanpo Fu, Yong Fang, Yang Liu
2025 — conf
AgileIR: Memory-Efficient Group Shifted Windows Attention for Lightweight Image Restoration.
ICANN (2)
Hongyi Cai, Mohammad Mahdinur Rahman, Jingyu Wu, Wenzhen Dong, Jie Li
2025 J jnl
AutoDebias: Automated Framework for Debiasing Text-to-Image Models.
CoRR
Hongyi Cai, Mohammad Mahdinur Rahman, Mingkang Dong, Jie Li, Muxin Pu, Zhili Fang, Yinan Peng, Hanjun Luo, Yang Liu
2025 B conf
CFPFormer: Cross Feature-Pyramid Transformer Decoder for Medical Image Segmentation.
IJCNN
Hongyi Cai, Mohammad Mahdinur Rahman, Wenzhen Dong, Jingyu Wu
2025 J jnl
Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment.
CoRR
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
2025 A* conf
How Effective is In-Context Learning with Large Language Models for Rare Cell Identification in Single-Cell Expression Data?
ICDM
Huaiyuan Yao, Zhenxiao Cao, Zhongman Wang, Xiewei Ni, Jinyan Dong, Hongyi Cai, Yuqiang Han, Xiao Luo
2025 — conf
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning.
EMNLP (Findings)
Hongyi Cai, Jie Li, Mohammad Mahdinur Rahman, Wenzhen Dong
2025 J jnl
MergeIT: From Selection to Merging for Efficient Instruction Tuning.
CoRR
Hongyi Cai, Yuqian Fu, Hongming Fu, Bo Zhao
2025 J jnl
Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks.
CoRR
Jie Li, Hongyi Cai, Mingkang Dong, Muxin Pu, Shan You, Fei Wang, Tao Huang
2025 A* conf
To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts.
ICLR
Yukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra
2025 J jnl
VLA-Pruner: Temporal-Aware Dual-Level Visual Token Pruning for Efficient Vision-Language-Action Inference.
CoRR
Ziyan Liu, Yeqiu Chen, Hongyi Cai, Tao Lin, Shuo Yang, Zheng Liu, Bo Zhao
2024 J jnl
AccidentBlip2: Accident Detection With Multi-View MotionBlip2.
CoRR
Yihua Shao, Hongyi Cai, Xinwei Long, Weiyi Lang, Zhe Wang, Haoran Wu, Yan Wang, Jiayi Yin, Yang Yang, Yisheng Lv, Zhen Lei
2024 J jnl
AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration.
CoRR
Hongyi Cai, Mohammad Mahdinur Rahman, Mohammad Shahid Akhtar, Jie Li, Jingyu Wu, Zhili Fang
2024 J jnl
CFPFormer: Feature-pyramid like Transformer Decoder for Segmentation and Detection.
CoRR
Hongyi Cai, Mohammad Mahdinur Rahman, Jingyu Wu, Yulun Deng
2024 B conf
Cross-Modal Alignment of Local and Global Features for Zero-Shot Chinese Character Recognition.
ICIP
Hongyi Cai, Anna Zhu
2024 J jnl
Enhancing Large Language Models' Situated Faithfulness to External Contexts.
CoRR
Yukun Huang, Sanxing Chen, Hongyi Cai, Bhuwan Dhingra
2023 — conf
An Adaptive Gradient Privacy-Preserving Algorithm for Federated XGBoost.
CACML
Hongyi Cai, Jianping Cai, Lan Sun
2020 B conf
Improving High Dynamic Range Image Based Light Measurement.
SMC
Hankun Li, Hongyi Cai, Guanghui Wang
2011 — conf
A Camera-Aided Legibility Assessment Protocol of Displays for Enhanced Human-Computer Interaction.
HCI (10)
Hongyi Cai