Google Research announced on August 17th that its deep learning method PhotoScan, which estimates body composition from smartphone images, can help classify insulin resistance nearly as well as a dual…
Researchers at an undisclosed institution present CV, a computer vision framework that estimates the fatigue life of lightweight alloy steels from optical micrographs, achieving an R² of 0.93 and RMSE…
PyTorch's DistributedDataParallel (DDP) enables multi-GPU training by synchronizing gradients across all GPUs via AllReduce, ensuring each GPU maintains identical model weights. The article explains t…
Kernel Forge, an open-source agentic harness for LLM-based generation and optimization of CUDA kernels, achieves speedups of up to 2.83× on softmax in Gemma 4 E2B and 1.70× on group_norm in Stable Dif…
ANEForge, a new open-source Python package, compiles tensor graphs directly into programs for the Apple Neural Engine (ANE) and runs them without CoreML, enabling both inference and training on the ch…
A new open-source integration for Hugging Face Trainer, TraceML, diagnoses whether GPU underutilization is caused by data-loading bottlenecks or model compute limits. The tool, built by an unnamed dev…
A study from arXiv reveals that a benchmark leak caused an OOD detector's AUROC to drop to 0.326, well below chance, because the designated OOD class was actually in the training set. After deleting t…
NVIDIA TensorRT's IProgressMonitor API lets developers make long-running engine builds observable and cancelable in Python and C++, preventing wasted GPU-hours in agent workflows. The interface provid…
ForensicNet, a lightweight deep learning framework combining MobileNetV2 with Convolutional Block Attention Modules, achieves 92.4% accuracy and 90.8% precision on face identification across 15,000 im…
A developer compares PyTorch and TensorFlow for computer vision projects, noting that PyTorch dominates research with dynamic computation graphs and recent performance improvements via torch.compile()…
Efficient Long-hOrizon (ELO) learning, a new learned optimizer, surpasses traditional models like AdamW and Muon across diverse tasks including language modeling and image classification, requiring le…
A new decision framework for cross-habitat marine species recognition shows that pairing a frozen DINOv2 foundation model with a linear classifier and just 10-20 labeled images per species achieves re…
A developer built an artist attribution system using PyTorch and a pretrained ResNet-50 model. The system classifies paintings by artist with top-3 predictions, leveraging transfer learning for effici…
Researchers developed topology-informed neural networks that integrate topological data analysis with deep learning to improve flood detection in satellite imagery, achieving more robust and interpret…
MemryX's MX3 edge AI accelerator achieved 1796 FPS on ResNet-50 at 14 TFLOPS, exceeding the company's published benchmark of 1778 FPS by 1% in independent testing. The measurement follows a standardiz…
DeepX's M1 edge AI accelerator achieves 1,067 FPS on ResNet-50 with a power efficiency of 515.02 FPS/W, as measured by independent benchmarking using the DX-ALL suite. The results confirm the manufact…
Mario Bergeron published Part 4 of his Edge AI Power Benchmarking series on Hackster.io, applying an independent power-measurement methodology to the Axelera Metis accelerator. The post cites vendor-p…
A developer argues that balanced ternary (-1, 0, +1) could replace binary for AI hardware, citing 20× model compression, 3× inference speedup, and 8× power reduction. Microsoft's BitNet b1.58 demonstr…
Researchers from multiple institutions evaluated machine learning and deep learning models for satellite-derived bathymetry using Sentinel-2 imagery, finding that preserving spatial continuity during …