Fanhu Zeng

28 papers A* 5Journal 21Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients.
CoRR
Ziwei Xiang, Fanhu Zeng, Hongjian Fang, Rui-Qi Wang, Renxing Chen, Yanan Zhu, Yi Chen, Peipei Yang, Xu-Yao Zhang
2026 J jnl
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation.
CoRR
Lei Xin, Yuhao Zheng, Ke Cheng, Changjiang Jiang, Zifan Zhang, Fanhu Zeng
2026 J jnl
Imagination Helps Visual Reasoning, But Not Yet in Latent Space.
CoRR
You Li, Chi Chen, Yanghao Li, Fanhu Zeng, Kaiyu Huang, Jinan Xu, Maosong Sun
2026 A* conf
TR-DQ: Time-Rotation Diffusion Quantization.
AAAI
Yihua Shao, Deyang Lin, Minxi Yan, Siyu Chen, Fanhu Zeng, Minwen Liao, Ao Ma, Ziyang Yan, Haozhe Wang, Yan Wang, Zhi Chen, Xiaofeng Cao, Haotong Qin, Hao Tang, Jingcai Guo
2025 J jnl
A Comprehensive Survey on Continual Learning in Generative Models.
CoRR
Haiyang Guo, Fanhu Zeng, Fei Zhu, Jiayi Wang, Xukai Wang, Jingang Zhou, Hongbo Zhao, Wenzhuo Liu, Shijie Ma, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu
2025 — conf
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing.
ACL (Findings)
Xuanle Zhao, Xuexin Liu, Haoyue Yang, Xianzhen Luo, Fanhu Zeng, Jianling Li, Qi Shi, Chi Chen
2025 J jnl
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing.
CoRR
Xuanle Zhao, Xuexin Liu, Haoyue Yang, Xianzhen Luo, Fanhu Zeng, Jianling Li, Qi Shi, Chi Chen
2025 A* conf
EventVAD: Training-Free Event-Aware Video Anomaly Detection.
ACM Multimedia
Yihua Shao, Haojin He, Sijie Li, Siyu Chen, Xinwei Long, Fanhu Zeng, Yuxuan Fan, Muyang Zhang, Ziyang Yan, Ao Ma, Xiaochen Wang, Hao Tang, Yan Wang, Shuyan Li
2025 J jnl
EventVAD: Training-Free Event-Aware Video Anomaly Detection.
CoRR
Yihua Shao, Haojin He, Sijie Li, Siyu Chen, Xinwei Long, Fanhu Zeng, Yuxuan Fan, Muyang Zhang, Ziyang Yan, Ao Ma, Xiaochen Wang, Hao Tang, Yan Wang, Shuyan Li
2025 J jnl
Federated Continual Instruction Tuning.
CoRR
Haiyang Guo, Fanhu Zeng, Fei Zhu, Wenzhuo Liu, Da-Han Wang, Jian Xu, Xu-Yao Zhang, Cheng-Lin Liu
2025 — conf
HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model.
ACL (1)
Haiyang Guo, Fanhu Zeng, Ziwei Xiang, Fei Zhu, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu
2025 J jnl
HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model.
CoRR
Haiyang Guo, Fanhu Zeng, Ziwei Xiang, Fei Zhu, Da-Han Wang, Xu-Yao Zhang, Cheng-Lin Liu
2025 A* conf
Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection.
ICLR
Fanhu Zeng, Zhen Cheng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang
2025 J jnl
MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark.
CoRR
Haiyang Guo, Fei Zhu, Hongbo Zhao, Fanhu Zeng, Wenzhuo Liu, Shijie Ma, Da-Han Wang, Xu-Yao Zhang
2025 A* conf
MambaIC: State Space Models for High-Performance Learned Image Compression.
CVPR
Fanhu Zeng, Hao Tang, Yihua Shao, Siyu Chen, Ling Shao, Yan Wang
2025 J jnl
MambaIC: State Space Models for High-Performance Learned Image Compression.
CoRR
Fanhu Zeng, Hao Tang, Yihua Shao, Siyu Chen, Ling Shao, Yan Wang
2025 A* conf
ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt.
EMNLP
Fanhu Zeng, Fei Zhu, Haiyang Guo, Xu-Yao Zhang, Cheng-Lin Liu
2025 J jnl
Parameter Efficient Merging for Multimodal Large Language Models with Complementary Parameter Adaptation.
CoRR
Fanhu Zeng, Haiyang Guo, Fei Zhu, Li Shen, Hao Tang
2025 J jnl
TR-DQ: Time-Rotation Diffusion Quantization.
CoRR
Yihua Shao, Deyang Lin, Fanhu Zeng, Minxi Yan, Muyang Zhang, Siyu Chen, Yuxuan Fan, Ziyang Yan, Haozhe Wang, Jingcai Guo, Yan Wang, Haotong Qin, Hao Tang
2025 J jnl
Token Reduction Should Go Beyond Efficiency in Generative Models - From Vision, Language to Multimodality.
CoRR
Zhenglun Kong, Yize Li, Fanhu Zeng, Lei Xin, Shvat Messica, Xue Lin, Pu Zhao, Manolis Kellis, Hao Tang, Marinka Zitnik
2025 J jnl
Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration.
CoRR
Fanhu Zeng, Deli Yu, Zhenglun Kong, Hao Tang
2025 J jnl
Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models.
CoRR
Fanhu Zeng, Zhen Cheng, Fei Zhu, Xu-Yao Zhang
2025 J jnl
VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
CoRR
Hongbo Zhao, Meng Wang, Fei Zhu, Wenzhuo Liu, Bolin Ni, Fanhu Zeng, Gaofeng Meng, Zhaoxiang Zhang
2024 J jnl
CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models.
CoRR
Zhong-Zhi Li, Ming-Liang Zhang, Fei Yin, Zhi-Long Ji, Jin-Feng Bai, Zhen-Ru Pan, Fanhu Zeng, Jian Xu, Jiaxin Zhang, Cheng-Lin Liu
2024 J jnl
DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning.
CoRR
Haiyang Guo, Fei Zhu, Fanhu Zeng, Bing Liu, Xu-Yao Zhang
2024 J jnl
Enhancing Outlier Knowledge for Few-Shot Out-of-Distribution Detection with Extensible Local Prompts.
CoRR
Fanhu Zeng, Zhen Cheng, Fei Zhu, Xu-Yao Zhang
2024 J jnl
ModalPrompt:Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models.
CoRR
Fanhu Zeng, Fei Zhu, Haiyang Guo, Xu-Yao Zhang, Cheng-Lin Liu
2023 J jnl
PPT: Token Pruning and Pooling for Efficient Vision Transformers.
CoRR
Xin-Jian Wu, Fanhu Zeng, Xiudong Wang, Yunhe Wang, Xinghao Chen