A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Yuzhong Zhao, Yue Liu, Junpeng Liu, et al.
GMPO improves GRPO stability by replacing arithmetic mean with geometric mean of token rewards, reducing outlier sensitivity and boosting reasoning performance.
Emilio Ferrara
This survey explores early trends, datasets, and challenges in applying large language models to wearable sensor data for human activity recognition, health monitoring, and behavioral modeling.
Maria Rita Palattella, Mischa Döhler, Alfredo Grieco, et al.
This paper analyzes how 5G technologies can serve as a key enabler for the Internet of Things by addressing connectivity fragmentation and enabling ubiquitous, reliable, scalable, and cost-efficient IoT services.
Anna Gaulton, Louisa J. Bellis, A. Patrícia Bento, et al.
ChEMBL is an open-access database of manually curated bioactivity data for drug-like compounds, containing 5.4 million measurements across 1 million compounds and 5200 targets.
Humaid Al Naqbi, Zied Bahroun, Vian Ahmed
A PRISMA-based literature review of 159 papers analyzing how generative AI enhances productivity across multiple sectors, with bibliometric identification of ChatGPT as a dominant tool.
Unknown
ConvNets (NFNets) match Vision Transformers in performance when pre-trained on large datasets and fine-tuned on ImageNet, challenging the assumption that ViTs are inherently superior at scale.
Unknown
U-ViT proposes a Vision Transformer (ViT) architecture for image generation using diffusion models, treating all inputs as tokens.
Unknown
OWL ViT enables open-vocabulary object detection by adapting Vision Transformers with CLIP-style pre-training and bipartite matching loss.
Unknown
SoViT introduces compute-optimal shape scaling for vision transformers, achieving performance of models twice its size with equivalent compute.
Unknown
FastViT introduces RepMixer, a reparameterized token mixer, achieving fast inference with minimal accuracy loss in hybrid vision transformers.
Unknown
EfficientFormer revisits ViT design principles through latency analysis, identifies inefficient operators, and proposes a dimension-consistent design with a latency-driven slimming method for faster inference.
Unknown
MobileViT introduces a lightweight vision transformer that combines CNN and ViT strengths for efficient mobile deployment.