NVIDIA's new diffusion language models generate tokens in parallel and refine them iteratively, potentially breaking the latency limits of traditional autoregressive models and enabling self-correction.
AI2 releases EMO, a new MoE model pretrained to enable emergent modularity, allowing users to selectively use just 12.5% of experts for a task while maintaining near full-model performance.
NVIDIA trained the Nemotron OCR v2 model on 12 million synthetic images, achieving high accuracy (NED as low as 0.035) and high speed (34.7 pages/second on a single A100 GPU) across six languages, demonstrating that synthetic data is a key solution to the multilingual data bottleneck in OCR.
Holotron-12B optimizes inference efficiency and handles long contexts, becoming a powerful tool for high-performance computing agents, crucial for AI applications.
Lilian Weng explores how AI models can enhance reasoning and decision-making by simulating human thought processes, providing new insights for future model design.