Oceania
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection Xinlei Wang
This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data.
An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement
As societal awareness of climate change grows, corporate climate policy engagements are attracting attention.
A Benchmark for Interpretability Methods in Deep Neural Networks
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, Been Kim
Neural Information Processing Systems http://nips.cc/
On Tractable Computation of Expected Predictions
Pasha Khosravi, YooJung Choi, Yitao Liang, Antonio Vergari, Guy Van den Broeck
Finally, we illustrate how our framework can be used for exploratory data analysis.
KNG: The K-Norm Gradient Mechanism
Neural Information Processing Systems http://nips.cc/
Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections
This approach is however difficult to extend to the case in which one wants to compute an OT map (a Monge map) between the original measures.
Variational Bayes under Model Misspecification
However, models are rarely well-specified in practice.