Related papers: Target Concept Tuning Improves Extreme Weather For…

Recent progress in motion forecasting has been substantially driven by self-supervised pre-training. However, adapting pre-trained models for specific downstream tasks, especially motion prediction, through extensive fine-tuning is often…

Through exploiting a high level of parallelism enabled by graphics processing units, transformer architectures have enabled tremendous strides forward in the field of natural language processing. In a traditional masked language model,…

Fake news detection has been a critical task for maintaining the health of the online news ecosystem. However, very few existing works consider the temporal shift issue caused by the rapidly-evolving nature of news data in practice,…

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Precipitation nowcasting is critically important for meteorological forecasting. Deep learning-based Radar Echo Extrapolation (REE) has become a predominant nowcasting approach, yet it suffers from poor generalization due to its reliance on…

Fine-tuning is the primary mechanism for adapting foundation models to downstream tasks; however, standard approaches largely optimize task objectives in isolation and do not account for secondary yet critical alignment objectives (e.g.,…

Extreme weather events pose significant challenges, thereby demanding techniques for accurate analysis and precise forecasting to mitigate its impact. In recent years, deep learning techniques have emerged as a promising approach for…

Learning-based model predictive control has been widely applied in autonomous racing to improve the closed-loop behaviour of vehicles in a data-driven manner. When environmental conditions change, e.g., due to rain, often only the…

Time series forecasting always faces the challenge of concept drift, where data distributions evolve over time, leading to a decline in forecast model performance. Existing solutions are based on online learning, which continually organize…

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior…

Rapid intensification (RI) of tropical cyclones (TCs) poses a great challenge due to their highly nonlinear dynamics and inherent uncertainties. Conventional statistical dynamics and artificial intelligence prediction models typically rely…

In the field of autonomous driving, there have been many excellent perception models for object detection, semantic segmentation, and other tasks, but how can we effectively use the perception models for vehicle planning? Traditional…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Accurate time series forecasting models are often compromised by data drift, where underlying data distributions change over time, leading to significant declines in prediction performance. To address this challenge, this study proposes an…

Climate change is increasing the occurrence of extreme precipitation events, threatening infrastructure, agriculture, and public safety. Ensemble prediction systems provide probabilistic forecasts but exhibit biases and difficulties in…

With broad applications in various public services like aviation management and urban disaster warning, numerical precipitation prediction plays a crucial role in weather forecast. However, constrained by the limitation of observation and…

As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although…

Generating rare compositional concepts in text-to-image synthesis remains a challenge for diffusion models, particularly for attributes that are uncommon in the training data. While recent approaches, such as R2F, address this challenge by…

Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained…

Weather extremes are a major societal and economic hazard, claiming thousands of lives and causing billions of dollars in damage every year. Under climate change, their impact and intensity are expected to worsen significantly.…