Publications

• Large Language Model Agent: A Survey on Methodology, Applications and Challenges [Paper] [Resources]
  Junyu Luo, Weizhi Zhang, Ye Yuan, Yusheng Zhao, Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, Rongcheng Tu, Xiao Luo, Wei Ju, Zhiping Xiao, Yifan Wang, Meng Xiao, Chenwu Liu, Jingyang Yuan, Shichang Zhang, Yiqiao Jin, Fan Zhang, Xian Wu, Hanqing Zhao, Dacheng Tao, Philip S. Yu, Ming Zhang
  Preprint
• Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation
  Junyu Luo, Yuhao Tang, Yifan Wang, Xiao Luo, Zhizhuo Kou, Zhiping Xiao, Wei Ju, Wentao Zhang, Ming Zhang
  ICML 2025, CCF-A
• FinMME: A Financial Multi-Modal Evaluation Dataset
  Junyu Luo*, Zhizhuo KOU*, Liming Yang*, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong LIU, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo
  ACL 2025 Main, CCF-A
• Towards Efficient LLM Post Training: A Data-centric Perspective [Paper][Resources]
  Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang
  ACL 2025 Main, CCF-A
• Native sparse attention: Hardware-aligned and natively trainable sparse attention [Paper]
  Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, YX Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng
  ACL 2025 Main, CCF-A
• Cross-Domain Diffusion with Progressive Alignment for Efficient Adaptive Retrieval [Paper]
  Junyu Luo, Yusheng Zhao, Xiao Luo, Zhiping Xiao, Wei Ju, Li Shen, Dacheng Tao, Ming Zhang
  IEEE Transactions on Image Processing
  TIP 2025, CCF-A, JCR Q1, IF=10.8
• SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation [Paper] [Code]
  Junyu Luo, Xiao Luo, Xiusi Chen, Zhiping Xiao, Wei Ju, Ming Zhang
  NAACL 2025 Findings, CCF-B
• Future Matters for Present: Towards Effective Physical Simulation over Meshes [Paper]
  Xiao Luo, Junyu Luo, Huiyu Jiang, Hang Zhou, Zhiping Xiao, Wei Ju, Carl Yang, Ming Zhang, Yizhou Sun
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining
  SIGKDD 2025, CCF-A
• Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
  Yusheng Zhao, Qixin Zhang, Xiao Luo, Junyu Luo, Wei Ju, Zhiping Xiao, Ming Zhang
  ICML 2025, CCF-A
• Attention Bootstrapping for Multi-Modal Test-Time Adaptation [Paper]
  Yusheng Zhao, Junyu Luo, Xiao Luo, Jinsheng Huang, Jingyang Yuan, Zhiping Xiao, Ming Zhang
  AAAI Conference on Artificial Intelligence
  AAAI 2025, CCF-A
• TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs [Paper]
  Yusheng Zhao, Changhu Wang, Xiao Luo, Junyu Luo, Wei Ju, Zhiping Xiao, Ming Zhang
  AAAI Conference on Artificial Intelligence
  AAAI 2025, CCF-A
• DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation [Paper]
  Pengyun Wang, Yadi Cao, Chris Russell, Siyu Heng, Junyu Luo, Yanxin Shen, Xiao Luo
  Transactions on Machine Learning Research
  TMLR 2025

• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation [Paper][Code]
  Junyu Luo, Yiyang Gu, Xiao Luo, Wei Ju, Zhiping Xiao, Yusheng Zhao, Jingyang Yuan, Ming Zhang
  IEEE Transactions on Pattern Analysis and Machine Intelligence
  TPAMI 2024, CCF-A, JCR Q1, IF=23.6
• Rank and Align: Towards Effective Source-free Graph Domain Adaptation [Paper]
  Junyu Luo, Zhiping Xiao, Yifan Wang, Xiao Luo, Jingyang Yuan, Wei Ju, Langechuan Liu, Ming Zhang
  International Joint Conference on Artificial Intelligence
  IJCAI 2024, CCF-A
• Multi-View Teacher with Curriculum Data Fusion for Robust Unsupervised Domain Adaptation [Paper]
  Yuhao Tang*, Junyu Luo*, Ling Yang, Xiao Luo, Wentao Zhang, Bin Cui
  IEEE International Conference on Data Engineering
  ICDE 2024, CCF-A
• A survey of data-efficient graph learning [Paper]
  Wei Ju, Siyu Yi, Yifan Wang, Qingqing Long, Junyu Luo, Zhiping Xiao, Ming Zhang
  International Joint Conference on Artificial Intelligence
  IJCAI 2024, CCF-A
• EGODE: An event-attended graph ODE framework for modeling rigid dynamics [Paper]
  Jingyang Yuan, Gongbo Sun, Zhiping Xiao, Hang Zhou, Xiao Luo, Junyu Luo, Yusheng Zhao, Wei Ju, Ming Zhang
  Annual Conference on Neural Information Processing Systems
  NeurIPS 2024, CCF-A

• 3D-SPS: Single-stage 3D visual grounding via referred point progressive selection [Paper] [Code]
  Junyu Luo*, Jiahui Fu*, Xianghao Kong, Chen Gao, Haibing Ren, Hao Shen, Huaxia Xia, Si Liu
  IEEE/CVF Conference on Computer Vision and Pattern Recognition
  CVPR 2022, CCF-A, Oral

• FedSkel: efficient federated learning on heterogeneous systems with skeleton gradients update [Paper][Code]
  Junyu Luo, Jianlei Yang, Xucheng Ye, Xin Guo, Weisheng Zhao
  ACM International Conference on Information & Knowledge Management
  CIKM 2021, CCF-B
• Transrefer3D: Entity-and-relation aware transformer for fine-grained 3d visual grounding [Paper] [Code]
  Dailan He*, Yusheng Zhao*, Junyu Luo*, Tianrui Hui, Shaofei Huang, Aixi Zhang, Si Liu
  ACM International Conference on Multimedia
  ACM MM 2021, CCF-A

• SparseTrain: Exploiting dataflow sparsity for efficient convolutional neural networks training [Paper]
  Pengcheng Dai, Jianlei Yang, Xucheng Ye, Xingzhou Cheng, Junyu Luo, Linghao Song, Yiran Chen, Weisheng Zhao
  ACM/IEEE Design Automation Conference
  DAC 2020, CCF-A
• Accelerating CNN training by pruning activation gradients [Paper]
  Xucheng Ye, Pengcheng Dai, Junyu Luo, Xin Guo, Yingjie Qi, Jianlei Yang, Yiran Chen
  European Conference on Computer Vision
  ECCV 2020, CCF-B