Oct 2026· Visual Intelligence· Vol 4· 0 citations· 26 references
Heat Transfer and Optimization
Abstract
Efficient thermal management is critical in data centers, where computational fluid dynamics (CFD) simulations provide high-fidelity airflow and temperature predictions but remain computationally demanding and time-intensive. While data-driven methods have emerged as promising alternatives, most existing works are limited to small-scale or 2D flow simulations and face challenges when extended to complex 3D domains. To overcome these challenges, we present PIGNN3D, a physics-informed graph neural network designed for fast and efficient 3D thermal field simulation in data centers. PIGNN3D introduces architectural simplifications and optimized message passing to significantly accelerate training and reduce memory usage, while preserving the physical consistency of CFD-based modelling. Experimental results demonstrate significant reduction in video random access memory (VRAM) usage and faster convergence while maintaining accuracy comparable to other methods. This advancement brings artificial intelligence (AI)-driven thermal simulation closer to practical deployment for speedy and sustainable data center management.
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9
This paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging directions from YOLOv5 through YOLO27, and examines detection, segmentation, depth, classification, pose, oriented detection, tracking, export, quantization, and deplo...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
