Using generative AI to help scientists synthesize complex materials

Generative AI models have been used to create enormous libraries of theoretical materials that could help solve all kinds of ...

Hard-to-synthesize materials revived using AI: An LLM-based materials redesign technology

A research team led by Prof. Yousung Jung of the Department of Chemical and Biological Engineering at Seoul National University (SNU) has developed an innovative AI-based technology that uses large ...

This tree search framework hits 98.7% on documents where vector search fails

PageIndex, a new open-source framework, achieves 98.7% accuracy on complex document retrieval by using tree search instead of ...
조선일보

Samsung Biologics expands Korea CRDMO lead with MCB and vector services

Samsung Biologics is further strengthening its "super-gap" strategy in the contract development organization (CDO) field for biopharmaceuticals. By linking the contract research organization (CRO) ...
Microsoft

Autoregressive Speech Synthesis without Vector Quantization

We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from ...
Frontiers

High-fidelity medical image generation: controllable synthesis of high-resolution medical images via hierarchical fusion in vector-quantized generative networks

Objective: High-resolution medical images are scarce, and existing image generation methods perform poorly at high resolutions, struggling with the representation of small lesions, loss of detailed ...
IEEE

Texture synthesis by Support Vector Machines

Abstract: We introduce a simple texture synthesis method based on Support Vector Machines (SVM). Although SVM has been effectively used for various pattern recognition tasks, there is no report ...