相关论文: WeatherQA: Can Multimodal Language Models Reason a…

While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream Reinforcement Fine-Tuning (RFT) can induce…

Multimodal Large Language Models (MLLMs) have achieved significant advancements in tasks like Visual Question Answering (VQA) by leveraging foundational Large Language Models (LLMs). However, their abilities in specific areas such as visual…

Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are primarily constructed from high-quality images captured under idealized conditions. This raises…

Timely and accurate forecasts of severe weather events are essential for early warning and for constraining downstream analysis and decision-making. Since severe weather events prediction still depends on subjective, time-consuming expert…

Temporal reasoning is fundamental for large language models (LLMs) to comprehend the world. Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal…

Quality analysis of weather forecasts is an essential topic in meteorology. Although traditional score-based evaluation metrics can quantify certain forecast errors, they are still far from meteorological experts in terms of descriptive…

Severe convective storms are among the most dangerous weather phenomena and accurate forecasts mitigate their impacts. The recently released suite of AI-based weather models produces medium-range forecasts within seconds, with a skill…

Weather forecasting is crucial for public safety, disaster prevention and mitigation, agricultural production, and energy management, with global relevance. Although deep learning has significantly advanced weather prediction, current…

Forecasting from atmospheric soundings is a fundamental task in operational meteorology, often requiring structured visual reasoning over Skew-T log-P diagrams by human forecasters. While recent advances in Vision-Language Models (VLMs)…

Many real-world tasks require an agent to reason jointly over text and visual objects, (e.g., navigating in public spaces), which we refer to as context-sensitive text-rich visual reasoning. Specifically, these tasks require an…

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks. However, their robustness against textual misinformation remains under-explored. While existing research has…

Recent advances in Vision-Language Models (VLMs) have demonstrated impressive capabilities in perception and reasoning. However, the ability to perform causal inference -- a core aspect of human cognition -- remains underexplored,…

Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However,…

Vision Language Models (VLMs) have recently shown significant advancements in video understanding, especially in feature alignment, event reasoning, and instruction-following tasks. However, their capability for counterfactual reasoning,…

Numerical weather forecasting using high-resolution physical models often requires extensive computational resources on supercomputers, which diminishes their wide usage in most real-life applications. As a remedy, applying deep learning…

Large multimodal models extend the impressive capabilities of large language models by integrating multimodal understanding abilities. However, it is not clear how they can emulate the general intelligence and reasoning ability of humans.…

Multimodal information, together with our knowledge, help us to understand the complex and dynamic world. Large language models (LLM) and large multimodal models (LMM), however, still struggle to emulate this capability. In this paper, we…

Within the multimodal field, large vision-language models (LVLMs) have made significant progress due to their strong perception and reasoning capabilities in the visual and language systems. However, LVLMs are still plagued by the two…

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene…

Event forecasting is a challenging, yet important task, as humans seek to constantly plan for the future. Existing automated forecasting studies rely mostly on structured data, such as time-series or event-based knowledge graphs, to help…