Generalizing from Limited Resources in the Open World

This book presents the Proceedings from the Second International Workshop GLOW 2024 held in conjunction with the International Joint Conference on Artificial Intelligence, IJCAI 2024, in Jeju Island, South Korea, in August 2024.

The 11 full papers and 4 short papers included in this book were carefully reviewed and selected from 22 submissions. They were organized in topical sections as follows: efficient methods for low-resource hardware; efficient fintuning with limited data; advancements in multimodal systems; recognition and reasoning in the open world.

Inhalt

Efficient Methods for Low-resource Hardware.- Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor.- Toward Efficient Deep Spiking Neuron Networks: A Survey On Compression.- Towards Efficient Fault Detection of UHV DC Circuit Breakers.- Robust Autonomous Unmanned Aerial Vehicle System for Efficient Tracking of Moving Objects.- Efficient Fintuning with Limited Data.- Entity Augmentation for Efficient Classification of Vertically Partitioned Data with Limited Overlap.-CafeLLM: Context-Aware Fine-Grained Semantic Clustering using Large Language Models.- Adapter-Based Contextualized Meta Embeddings.- Advancements in Multimodal Systems.- MADP: Multi-modal Sequence Learning for Alzheimer's Disease Prediction with Missing Data.- Multi-modal Spatiotemporal Forecasting via Cross-scale Operator Learning and Spatial Representation Aggregation.- Improved VLN-BERT with Reinforcing Endpoint Alignment for Vision-and-Language Navigation.- Bridging the Language Gap: Domain-Specific Dataset Construction for Medical LLMs.- Integrating Text-to-Image and Vision Language Models for Synergistic Dataset Generation: The Creation of Synergy-General-Multimodal Pairs.- Recognition and Reasoning in the Open World.- Semantic-Degrade Learning Framework for Open World Object Detection.- Multi-modal Prompts with Feature Decoupling for Open-Vocabulary Object Detection.- YOLO-FCNET: Enhancing SAR Ship Detection with Fourier Convolution in YOLOv8.