Though artificial intelligence (AI) has shown great success in diverse domains such as computer vision, natural language processing, and speech recognition, its heavy dependence on vast amounts of data and computational resources poses challenges for its applicability in open-world scenarios with limited data and computational capacities. In this workshop, we aim to bring data-efficient and computation-efficient AI researchers together to share ideas about their recent research and discuss future directions for the generalization of artificial intelligence models in an open-world setting. We hope to provide a forum to exchange ideas and offer new insights to address this generalization problem of AI models, advancing the development of real-world AI applications. 

We invite submissions on any aspect of generalizing from limited resources in the open world. We welcome research contributions related to the following (but not limited to) topics: 

• Transferability Metrics for Object Detection （Louis Fouquet, Simona Maggio and Léo Dreyfus-Schmidt）

• On Orderings of Probability Vectors and Unsupervised Performance Estimation（Muhammad Maaz, Rui Qiao, Yiheng Zhou and Renxian Zhang）

• Analysis on Effects of Fault Elements in Memristive Neuromorphic Systems（Hyun-Jong Lee and Jae-Han Lim)

• Breaking On-device Training Memory Wall: A Systematic Survey （Shitian Li, Chunlin Tian, Kahou Tam, Ma Rui and Li Li)

• Learning Compact Neural Networks with Deep Overparameterised Multitask Learning （Shen Ren and Haosen Shi)

• SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores（Zhiyu Mei, Wei Fu, Guangju Wang, Huanchen Zhang and Yi Wu)

• DiffuseExpand: Expanding Dataset for 2D Medical Image Segmentation Using Diffusion Models（Shao Shitong, Yuan Xiaohan, Huang Zhen, Qiu Ziming, Wang Shuai and Zhou Kevin)

• Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation（Shuai Wang, Daoan Zhang, Zipei Yan, Shitong Shao and Rui Li)

• A Traffic Anomaly Detection System Based on Siamese Network（Zinuo Yin, Tao Hu and Hailong Ma)

• Challenges and Prospects of Deep Learning Model Compression（Ge Yang and Congcong Geng)

• Discrepant Semantic Diffusion for Transfer Learning（Shihao Bai)

• SMP: Stable Mathematics and Physics Embedding for Motion Prediction（Yudie Wang and Yudie Wang)

• Self-supervised Edge Perception Learning Framework for VHR Images Classification with Limited Labeling Samples（Guangfei Li, Quanxue Gao, Jungong Han and Xinbo Gao)

• Instance Adaptive Prototypical Contrastive Embedding for Generalized Zero Shot Learning（Riti Paul, Sahil Vora and Baoxin Li)

• Feature Consistency Distillation for Indoor 3D Object Detection（Ze Yuan, Ke Xu, Junran Wu, Jianhao Li, Xueyuan Chen, Ziqi Zhao and Jiaheng Liu)

• Locating adversarial patches in the physical world（Siyang Wu, Chenhao Weng, Jiejie Zhao and Jiakai Wang)

• LB-KBQA: Large-language-model and BERT based KBQA（Yan Zhao and Zhongyun Li)

• Decision Fusion Network with Perception Fine-tuning for Defect Classification（Xiaoheng Jiang, Shilong Tian, Zhiwen Zhu, Yang Lu, Hao Liu, Li Chen, Shupan Li and Mingliang Xu)

• Self-adaptive hyper parameter tuning in advertisement ranking using reinforcement learning（Zizhe Gao, Zhenghui Hu and Qingjie Liu)

• Generalization between Different Viewpoints with A Feature Selection Method for Vehicle Re-identification（Kai Lv, Shuai Han and Youfang Lin)