Full Information
Full information research explores how to effectively utilize and manage information across diverse contexts, aiming to optimize information extraction, fusion, and utilization for improved decision-making and problem-solving. Current research focuses on developing advanced models, such as transformers and graph neural networks, to process and analyze various data types (e.g., logs, text, sensor data), often incorporating techniques like information propagation and entropy-based heuristics for enhanced performance. This field is significant for its potential to improve anomaly detection, prediction accuracy in complex systems (e.g., financial markets, healthcare), and the efficiency of information-seeking tasks, ultimately impacting various scientific disciplines and practical applications.
Papers
F-SE-LSTM: A Time Series Anomaly Detection Method with Frequency Domain Information
Yi-Xiang Lu, Xiao-Bo Jin, Jian Chen, Dong-Jie Liu, Guang-Gang Geng
Characterizing Information Shared by Participants to Coding Challenges: The Case of Advent of Code
Francesco Cauteruccio, Enrico Corradini, Luca Virgili
Learning to Look: Seeking Information for Decision Making via Policy Factorization
Shivin Dass, Jiaheng Hu, Ben Abbatematteo, Peter Stone, Roberto Martín-Martín
Context is Key: A Benchmark for Forecasting with Essential Textual Information
Andrew Robert Williams, Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin
Probing Ranking LLMs: Mechanistic Interpretability in Information Retrieval
Tanya Chowdhury, James Allan