Full-text search across 7093 articles. Combine with topic and date filters; results sorted by relevance.
Cosmologists trained an AI neural network on simulations of the standard model of cosmology, then tested whether that pre-training would help or hinder the AI's investigations into new physics. The AI developed biases th…
VisionAId, a new Android app, turns smartphones into visual assistants for the visually impaired using six on-device deep learning models and optional cloud-based Google Gemini Flash. The app features few-shot learning f…
Fine-tuning adapts a general pre-trained language model to perform a specific task by continuing its training on a smaller, task-specific dataset, allowing it to gain deep domain knowledge and understand required formats…
A new framework combining convolutional neural networks, long short-term memory, and reinforcement learning improves EEG-based brain-computer interface movement decoding, achieving a 41.5% relative gain in mean correlati…
Richard Sutton, the 2024 Turing Award winner and reinforcement learning pioneer, has launched Oak Lab in Toronto to develop AI agents capable of continuous learning, challenging current deep learning methods he calls 'we…
TabPack, a new ensemble of multilayer perceptrons for tabular data, minimizes hyperparameter tuning by sampling configurations in parallel and selecting the best members on the fly. It achieves competitive performance on…
Researchers introduced SelectTSL, a deep learning architecture for prompt-guided selective sound source localization that focuses only on user-specified targets in multi-source environments. The system outperforms standa…
Researchers have introduced Weight-Adjusted Gradients (WAG), a novel method for estimating parameter importance in Large Language Models that reveals a tiny subset of parameters disproportionately influencing model behav…
The Trump administration is reviving efforts to impose de facto bans on foreign open-source AI models, triggered by last week's launches of Moonshot AI's Kimi K3 and Alibaba's Qwen 3.8, according to an Axios report July …
Researchers have released Deep4ge, a massive dataset containing 14,227 training runs from 59 deep neural network programs to help detect faults in deep learning systems. The dataset includes 9,845 faulty runs created usi…
A new lightweight model, the Lightweight MultiScale AutoEncoder (LMSAE), achieves competitive anomaly detection performance with a model size under 500 KB, slashing inference latency by 9x and cutting power consumption b…
Researchers have developed a deep-learning method for MR elastography that reconstructs high-resolution images from highly undersampled data, achieving 2mm isotropic resolution in one minute with a total R value of 10. T…
Researchers developed Heterogeneous Frame Dispatch Scheduling (H-FraDS), a method that optimizes NVIDIA edge GPUs for autonomous systems by achieving a 2.36x speedup over standard DLA execution, reaching 125.93 frames pe…
A study using 134,376 hourly weather observations from Ioannina, Greece (2011-2026) found that hybrid CNN-GRU models outperform traditional recurrent networks in weather forecasting, achieving a Weighted Quotient Score o…
AutoSpec, a new neural network framework, reinvents spectral algorithms for large-scale tasks, achieving up to tenfold accuracy gains on real-world matrices. Developed by researchers, it adapts to input operators using c…
Researchers have developed HVR-Met, an AI system that improves extreme weather diagnostics by integrating expert knowledge and a novel feedback loop. The system sets a new benchmark for meteorological AI by focusing on a…
Researchers introduced CIPHER, a framework that reduces bias in medical AI by addressing multiple causal pathways linking sensitive attributes to image features. In tests on chest X-ray and dermoscopy benchmarks, CIPHER …
Researchers have developed a new compression algorithm for decentralized AI training that achieves up to 99% compression without degrading convergence, enabling billion-parameter models to be trained on low-end GPUs with…
Researchers introduced SAMPA, a Whisper-based model for prosodic segmentation in Brazilian Portuguese, achieving F1 scores of 0.731 on held-out test data and 0.796 on the MuPe-Diversidades dataset. The model outperforms …
Researchers have developed MiLSD, a sub-megabyte line segment detector for embedded systems, achieving a leap in performance on the ShanghaiTech Wireframe dataset from 10.6 to 24.1 sAP10 under a one-megabyte memory const…