Yongxian Wei

27 papers A* 8C 1Journal 18
YearRankTypeTitle / Venue / Authors
2026 A* conf
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation.
AAAI
Xinrui Chen, Hongxing Zhang, Fanyi Zeng, Yongxian Wei, Yizhi Wang, Xitong Ling, Guanghao Li, Chun Yuan
2026 J jnl
Task-Distributionally Robust Data-Free Meta-Learning.
IEEE Trans. Pattern Anal. Mach. Intell.
Zixuan Hu, Yongxian Wei, Li Shen, Zhenyi Wang, Baoyuan Wu, Chun Yuan, Dacheng Tao
2025 J jnl
Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler.
CoRR
Zixuan Hu, Li Shen, Zhenyi Wang, Yongxian Wei, Dacheng Tao
2025 J jnl
Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis for Large Reasoning Models.
CoRR
Yongxian Wei, Yilin Zhao, Li Shen, Xinrui Chen, Runxi Cheng, Sinan Du, Hao Yu, Gang Liu, Jiahong Yan, Chun Yuan, Dian Li
2025 A* conf
LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs.
CVPR
Zixuan Hu, Yongxian Wei, Li Shen, Chun Yuan, Dacheng Tao
2025 J jnl
Mixture of Neuron Experts.
CoRR
Runxi Cheng, Yuchen Guan, Yucheng Ding, Qingguo Hu, Yongxian Wei, Chun Yuan, Yelong Shen, Weizhu Chen, Yeyun Gong
2025 A* conf
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent.
ICML
Yongxian Wei, Anke Tang, Li Shen, Zixuan Hu, Chun Yuan, Xiaochun Cao
2025 J jnl
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent.
CoRR
Yongxian Wei, Anke Tang, Li Shen, Chun Yuan, Xiaochun Cao
2025 J jnl
OmniAlpha: A Sequence-to-Sequence Framework for Unified Multi-Task RGBA Generation.
CoRR
Hao Yu, Jiabo Zhan, Zile Wang, Jinglin Wang, Huaisong Zhang, Hongyu Li, Xinrui Chen, Yongxian Wei, Chun Yuan
2025 A* conf
Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation.
ICLR
Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Chun Yuan, Dacheng Tao
2025 J jnl
Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation.
CoRR
Xinrui Chen, Hongxing Zhang, Fanyi Zeng, Yongxian Wei, Yizhi Wang, Xitong Ling, Guanghao Li, Chun Yuan
2025 J jnl
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications.
CoRR
Zixuan Hu, Yongxian Wei, Li Shen, Zhenyi Wang, Lei Li, Chun Yuan, Dacheng Tao
2025 J jnl
Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging.
CoRR
Yongxian Wei, Runxi Cheng, Weike Jin, Enneng Yang, Li Shen, Lu Hou, Sinan Du, Chun Yuan, Xiaochun Cao, Dacheng Tao
2025 J jnl
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction.
CoRR
Sinan Du, Jiahao Guo, Bo Li, Shuhao Cui, Zhengzhuo Xu, Yifu Luo, Yongxian Wei, Kun Gai, Xinggang Wang, Kai Wu, Chun Yuan
2025 J jnl
Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors.
CoRR
Runxi Cheng, Feng Xiong, Yongxian Wei, Wanyun Zhu, Chun Yuan
2025 A* conf
Whoever Started the interference Should End It: Guiding Data-Free Model Merging via Task Vectors.
ICML
Runxi Cheng, Feng Xiong, Yongxian Wei, Wanyun Zhu, Chun Yuan
2024 J jnl
FREE: Faster and Better Data-Free Meta-Learning.
CoRR
Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, Dacheng Tao
2024 A* conf
Free: Faster and Better Data-Free Meta-Learning.
CVPR
Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, Dacheng Tao
2024 J jnl
Learn To Learn More Precisely.
CoRR
Runxi Cheng, Yongxian Wei, Xianglong He, Wanyun Zhu, Songsong Huang, Fei Richard Yu, Fei Ma, Chun Yuan
2024 J jnl
Meta-Learning Without Data via Unconditional Diffusion Models.
IEEE Trans. Circuits Syst. Video Technol.
Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Lei Li, Yu Li, Chun Yuan
2024 A* conf
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications.
ICML
Zixuan Hu, Yongxian Wei, Li Shen, Zhenyi Wang, Lei Li, Chun Yuan, Dacheng Tao
2024 A* conf
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models.
ICML
Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Yu Li, Chun Yuan, Dacheng Tao
2024 J jnl
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models.
CoRR
Yongxian Wei, Zixuan Hu, Li Shen, Zhenyi Wang, Yu Li, Chun Yuan, Dacheng Tao
2024 J jnl
Task-specific Part Discovery for Fine-grained Few-shot Classification.
Mach. Intell. Res.
Yongxian Wei, Xiu-Shen Wei
2024 J jnl
Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs.
CoRR
Zixuan Hu, Yongxian Wei, Li Shen, Chun Yuan, Dacheng Tao
2023 J jnl
Task-Distributionally Robust Data-Free Meta-Learning.
CoRR
Zixuan Hu, Li Shen, Zhenyi Wang, Yongxian Wei, Baoyuan Wu, Chun Yuan, Dacheng Tao
2022 C conf
Zero-Shot Object Detection with Multi-label Context.
SEKE
Yongxian Wei, Yong Ma