4.21-4.25
Weekly Highlights!

Contains 12 HPC tutorials summary

MindGlide is expected to further improve the ability of medical staff to interpret and evaluate the effectiveness of treatment for MS patients

This method uses a one-class support vector machine (one-class SVM) to analyze the characteristic differences between niacinamide and niacin in UV spectra.

UNO is based on the FLUX model and can handle different input conditions in image generation tasks.

The DRAKES algorithm implements for the first time differentiable reward backpropagation for fully generated trajectories in a discrete diffusion model.

M2OST is a many-to-one regression Transformer model designed to jointly predict gene expression using different levels of pathological images.

HyperAI has compiled multiple material science data sets and one-click deployment tutorials, covering key areas such as quantum materials, inorganic materials, and crystal structures.

The protein engineering design platform VenusFactory achieves one-stop optimization of data retrieval/model training/benchmark evaluation, lowering the threshold for AI4S applications.

Contains DeepCoder-14B-Preview one-click deployment tutorial

Professor Luo Xiaozhou from the Shenzhen Institute of Advanced Technology of the Chinese Academy of Sciences shared the innovative application and practice of AI in the field of enzyme engineering

Contains InfiniteYou high-fidelity image generation model deployment tutorial

Phaseshift Technologies builds next-generation alloys and composites, with AI at the heart of the effort

The Shanghai Artificial Intelligence Laboratory and several well-known universities jointly proposed the MaMI (Modality-adaptive Medical Identifier) model with excellent performance

The University of Cambridge, together with other universities and research centers, launched the Aardvark Weather forecasting system, providing a new path for the development of future weather forecasting technology

The US NIH issued a document prohibiting Chinese users from accessing the SEER database, and the construction of domestic databases was accelerated

Dr. Yuan Fajie from Westlake University shared the latest research progress and team research results of protein language model at the "AI Protein Design Summit"

A team from the University of Tokyo in Japan developed the STAIG deep learning framework, which can integrate gene expression, spatial data, and histological images without alignment.

The Multi-Agent Dialogue (MAC) framework based on GPT-3.5 and GPT-4 significantly improves the diagnostic capabilities of LLMs and is expected to become an important auxiliary tool for doctors

Contains YOLOE one-click deployment tutorial

EchoONE, a unified segmentation model for multi-section echocardiography, can accurately segment the cardiac structure of multi-section echocardiography, effectively reducing the complexity of the design model

Aerial photography dataset summary

3.24-3.28
Weekly Highlights!

Professor Zhang Yang's team from the National University of Singapore proposed a high-precision RNA structure prediction framework DRfold2 based on deep learning, and the unsupervised contact prediction accuracy is higher than the existing methods

VISTA3D multimodal medical image segmentation model pioneered a 3D supervoxel feature extraction method, improving zero-sample performance by 50%

3.17-3.21
Weekly Highlights

Contains the "CSM Conversational Speech Generation Model Demo" tutorial

A new protein structure prediction method based on AlphaFold effectively solves the problem of disordered protein structure prediction

AcneDGNet’s deep learning algorithm is not only more accurate than junior dermatologists, but is also comparable to senior dermatologists in accuracy.

HyperAI invited Associate Professor Huang Hong, Dr. Zhou Dongzhan, Dr. Zhou Bingxin and other teachers to discuss the cutting-edge development of AI

4.21-4.25
Weekly Highlights!

Contains 12 HPC tutorials summary

MindGlide is expected to further improve the ability of medical staff to interpret and evaluate the effectiveness of treatment for MS patients

This method uses a one-class support vector machine (one-class SVM) to analyze the characteristic differences between niacinamide and niacin in UV spectra.

UNO is based on the FLUX model and can handle different input conditions in image generation tasks.

The DRAKES algorithm implements for the first time differentiable reward backpropagation for fully generated trajectories in a discrete diffusion model.

M2OST is a many-to-one regression Transformer model designed to jointly predict gene expression using different levels of pathological images.

HyperAI has compiled multiple material science data sets and one-click deployment tutorials, covering key areas such as quantum materials, inorganic materials, and crystal structures.

The protein engineering design platform VenusFactory achieves one-stop optimization of data retrieval/model training/benchmark evaluation, lowering the threshold for AI4S applications.

Contains DeepCoder-14B-Preview one-click deployment tutorial

Professor Luo Xiaozhou from the Shenzhen Institute of Advanced Technology of the Chinese Academy of Sciences shared the innovative application and practice of AI in the field of enzyme engineering

Contains InfiniteYou high-fidelity image generation model deployment tutorial

Phaseshift Technologies builds next-generation alloys and composites, with AI at the heart of the effort

The Shanghai Artificial Intelligence Laboratory and several well-known universities jointly proposed the MaMI (Modality-adaptive Medical Identifier) model with excellent performance

The University of Cambridge, together with other universities and research centers, launched the Aardvark Weather forecasting system, providing a new path for the development of future weather forecasting technology

The US NIH issued a document prohibiting Chinese users from accessing the SEER database, and the construction of domestic databases was accelerated

Dr. Yuan Fajie from Westlake University shared the latest research progress and team research results of protein language model at the "AI Protein Design Summit"

A team from the University of Tokyo in Japan developed the STAIG deep learning framework, which can integrate gene expression, spatial data, and histological images without alignment.

The Multi-Agent Dialogue (MAC) framework based on GPT-3.5 and GPT-4 significantly improves the diagnostic capabilities of LLMs and is expected to become an important auxiliary tool for doctors

Contains YOLOE one-click deployment tutorial

EchoONE, a unified segmentation model for multi-section echocardiography, can accurately segment the cardiac structure of multi-section echocardiography, effectively reducing the complexity of the design model

Aerial photography dataset summary

3.24-3.28
Weekly Highlights!

Professor Zhang Yang's team from the National University of Singapore proposed a high-precision RNA structure prediction framework DRfold2 based on deep learning, and the unsupervised contact prediction accuracy is higher than the existing methods

VISTA3D multimodal medical image segmentation model pioneered a 3D supervoxel feature extraction method, improving zero-sample performance by 50%

3.17-3.21
Weekly Highlights

Contains the "CSM Conversational Speech Generation Model Demo" tutorial

A new protein structure prediction method based on AlphaFold effectively solves the problem of disordered protein structure prediction

AcneDGNet’s deep learning algorithm is not only more accurate than junior dermatologists, but is also comparable to senior dermatologists in accuracy.

HyperAI invited Associate Professor Huang Hong, Dr. Zhou Dongzhan, Dr. Zhou Bingxin and other teachers to discuss the cutting-edge development of AI