Category: News

MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Predictioncs.AI updates on arXiv.org arXiv:2508.06859v2 Announce Type: replace
Abstract: 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 interpretation, end-to-end “AI weather station” systems are emerging but face three major challenges: (1) scarcity of severe weather event samples; (2) imperfect alignment between high-dimensional meteorological data and textual warnings; (3) current multimodal language models cannot effectively process high-dimensional meteorological inputs or capture their complex spatiotemporal dependencies. To address these challenges, we introduce MP-Bench, the first large-scale multimodal dataset for severe weather events prediction, comprising 421,363 pairs of raw multi-year meteorological data and corresponding text caption, covering a wide range of severe weather scenarios. On top of this dataset, we develop a Meteorology Multimodal Large Model (MMLM) that directly ingests 4D meteorological inputs. In addition, it is designed to accommodate the unique characteristics of 4D meteorological data flow, incorporating three plug-and-play adaptive fusion modules that enable dynamic feature extraction and integration across temporal sequences, vertical pressure layers, and spatial dimensions. Extensive experiments on MP-Bench show that MMLM achieves strong performance across multiple tasks, demonstrating effective severe weather understanding and representing a key step toward automated, AI-driven severe weather events forecasting systems. Our source code and dataset will be made publicly available.

 arXiv:2508.06859v2 Announce Type: replace
Abstract: 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 interpretation, end-to-end “AI weather station” systems are emerging but face three major challenges: (1) scarcity of severe weather event samples; (2) imperfect alignment between high-dimensional meteorological data and textual warnings; (3) current multimodal language models cannot effectively process high-dimensional meteorological inputs or capture their complex spatiotemporal dependencies. To address these challenges, we introduce MP-Bench, the first large-scale multimodal dataset for severe weather events prediction, comprising 421,363 pairs of raw multi-year meteorological data and corresponding text caption, covering a wide range of severe weather scenarios. On top of this dataset, we develop a Meteorology Multimodal Large Model (MMLM) that directly ingests 4D meteorological inputs. In addition, it is designed to accommodate the unique characteristics of 4D meteorological data flow, incorporating three plug-and-play adaptive fusion modules that enable dynamic feature extraction and integration across temporal sequences, vertical pressure layers, and spatial dimensions. Extensive experiments on MP-Bench show that MMLM achieves strong performance across multiple tasks, demonstrating effective severe weather understanding and representing a key step toward automated, AI-driven severe weather events forecasting systems. Our source code and dataset will be made publicly available. Read More  

How I Use AI to Convince Companies to Adopt SustainabilityTowards Data Science Discover how Claude can act as a Supply Chain Sustainability Analyst and guide companies toward greener, more efficient inventory management.
The post How I Use AI to Convince Companies to Adopt Sustainability appeared first on Towards Data Science.

 Discover how Claude can act as a Supply Chain Sustainability Analyst and guide companies toward greener, more efficient inventory management.
The post How I Use AI to Convince Companies to Adopt Sustainability appeared first on Towards Data Science. Read More  

How to Implement Functional Components of Transformer and Mini-GPT Model from Scratch Using Tinygrad to Understand Deep Learning InternalsMarkTechPost In this tutorial, we explore how to build neural networks from scratch using Tinygrad while remaining fully hands-on with tensors, autograd, attention mechanisms, and transformer architectures. We progressively build every component ourselves, from basic tensor operations to multi-head attention, transformer blocks, and, finally, a working mini-GPT model. Through each stage, we observe how Tinygrad’s simplicity
The post How to Implement Functional Components of Transformer and Mini-GPT Model from Scratch Using Tinygrad to Understand Deep Learning Internals appeared first on MarkTechPost.

 In this tutorial, we explore how to build neural networks from scratch using Tinygrad while remaining fully hands-on with tensors, autograd, attention mechanisms, and transformer architectures. We progressively build every component ourselves, from basic tensor operations to multi-head attention, transformer blocks, and, finally, a working mini-GPT model. Through each stage, we observe how Tinygrad’s simplicity
The post How to Implement Functional Components of Transformer and Mini-GPT Model from Scratch Using Tinygrad to Understand Deep Learning Internals appeared first on MarkTechPost. Read More  

Find Them All: Unveiling MLLMs for Versatile Person Re-identificationcs.AI updates on arXiv.org arXiv:2508.06908v2 Announce Type: replace-cross
Abstract: Person re-identification (ReID) aims to retrieve images of a target person from the gallery set, with wide applications in medical rehabilitation and public security. However, traditional person ReID models are typically uni-modal, resulting in limited generalizability across heterogeneous data modalities. Recently, the emergence of multi-modal large language models (MLLMs) has shown a promising avenue for addressing this issue. Despite this potential, existing methods merely regard MLLMs as feature extractors or caption generators, leaving their capabilities in person ReID tasks largely unexplored. To bridge this gap, we introduce a novel benchmark for underline{textbf{V}}ersatile underline{textbf{P}}erson underline{textbf{Re}}-underline{textbf{ID}}entification, termed VP-ReID. The benchmark includes 257,310 multi-modal queries and gallery images, covering ten diverse person ReID tasks. In addition, we propose two task-oriented evaluation schemes for MLLM-based person ReID. Extensive experiments demonstrate the impressive versatility, effectiveness, and interpretability of MLLMs in various person ReID tasks. Nevertheless, they also have limitations in handling a few modalities, particularly thermal and infrared data. We hope that VP-ReID can facilitate the community in developing more robust and generalizable cross-modal foundation models for person ReID.

 arXiv:2508.06908v2 Announce Type: replace-cross
Abstract: Person re-identification (ReID) aims to retrieve images of a target person from the gallery set, with wide applications in medical rehabilitation and public security. However, traditional person ReID models are typically uni-modal, resulting in limited generalizability across heterogeneous data modalities. Recently, the emergence of multi-modal large language models (MLLMs) has shown a promising avenue for addressing this issue. Despite this potential, existing methods merely regard MLLMs as feature extractors or caption generators, leaving their capabilities in person ReID tasks largely unexplored. To bridge this gap, we introduce a novel benchmark for underline{textbf{V}}ersatile underline{textbf{P}}erson underline{textbf{Re}}-underline{textbf{ID}}entification, termed VP-ReID. The benchmark includes 257,310 multi-modal queries and gallery images, covering ten diverse person ReID tasks. In addition, we propose two task-oriented evaluation schemes for MLLM-based person ReID. Extensive experiments demonstrate the impressive versatility, effectiveness, and interpretability of MLLMs in various person ReID tasks. Nevertheless, they also have limitations in handling a few modalities, particularly thermal and infrared data. We hope that VP-ReID can facilitate the community in developing more robust and generalizable cross-modal foundation models for person ReID. Read More  

Are AI Browsers Any Good? A Day with Perplexity’s Comet and OpenAI’s AtlasKDnuggets Understanding the underlying technology helps explain why AI browsers exhibit such uneven performance.

 Understanding the underlying technology helps explain why AI browsers exhibit such uneven performance. Read More  

RISAT’s Silent Promise: Decoding Disasters with Synthetic Aperture RadarTowards Data Science The high-resolution physics turning microwave echoes into real-time flood intelligence
The post RISAT’s Silent Promise: Decoding Disasters with Synthetic Aperture Radar appeared first on Towards Data Science.

 The high-resolution physics turning microwave echoes into real-time flood intelligence
The post RISAT’s Silent Promise: Decoding Disasters with Synthetic Aperture Radar appeared first on Towards Data Science. Read More  

5 Excel AI Lessons I Learned the Hard WayKDnuggets This article transforms the unwelcome experiences into five comprehensive frameworks that will elevate your Excel-based machine learning work.

 This article transforms the unwelcome experiences into five comprehensive frameworks that will elevate your Excel-based machine learning work. Read More