Earth system models overestimate river flow increases, research reveals

Understanding how water moves through the Earth system is fundamental to predicting climate impacts and ensuring sustainable ...
GitHub

FUDOKI: A Unified Multimodal Model Purely Based on Discrete Flow Matching (NeurIPS 2025 spotlight)

The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation within a single ...
Frontiers

Advanced Predictive Models for Subsurface Energy Storage and Resource Management

Subsurface reservoir engineering has become increasingly pivotal as the world intensifies its focus on sustainable energy systems and effective resource ...
IEEE

Text-Enriched Air Traffic Flow Modeling and Prediction Using Transformers

Abstract: The air traffic control paradigm is shifting from sector-based operations to flow-centric approaches to overcome sectors’ geographical limits. Modeling and predicting intersecting air ...
IEEE

A Stochastic Traffic Flow Model-Based Reinforcement Learning Framework For Advanced Traffic Signal Control

Abstract: In addressing the complex challenge of Traffic Signal Control (TSC), Deep Reinforcement Learning (DRL) has emerged as a popular solution. In traditional DRL methods applied to TSC problems, ...