awesome-ai4s

AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai

3.3k

GitHub Stars

648

Curated Resources

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me 55. 4d diffusion model alphafolding fills the gap in dynamic protein structure prediction resources from awesome-ai4s"

Installation instructions →

What's inside

AI+ Biopharmaceutical

4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance55. 4D diffusion model AlphaFolding fills the gap in dynamic protein structure prediction
Ab initio RNA structure prediction with composite language model and denoised end-to-end learning64. High-accuracy RNA structure prediction framework DRfold2 surpasses SOTA in multiple benchmarks
Accurate de novo design of high-affinity protein binding macrocycles using deep learning46. Macrocyclic peptide binder framework RFpeptides offers new possibilities for undruggable proteins
A conditional protein diffusion model generates artificial programmable endonuclease sequences with enhanced activity38. CPDiffusion model designs functional proteins fully automatically at an ultra-low cost
Advancing Protein Ensemble Predictions Across the Order–Disorder Continuum85. Generative model PepTron and new evaluation benchmark released, reshaping prediction capabilities for disordered protein ensembles
A generalist medical language model for disease diagnosis assistance54. Medical language model MedFound approaches expert physician reasoning capabilities

AI+ Materials Chemistry

Ab initio structure solutions from nanocrystalline powder diffraction data via diffusion models34. Generative AI structure solution method PXRDnet based on diffusion models successfully solves 200 complex simulated nanocrystals
Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function28. Deep learning model BETE-NET boosts superconducting material search efficiency by 5x
A comprehensive machine learning strategy for designing high-performance photoanode catalysts7. Using machine learning to optimize co-catalysts for BiVO(4) photoanodes
A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metal-organic frameworks14. Uni-MOF: A machine learning model predicting adsorption behavior in 3D MOF materials
Active Learning Guided Discovery of High Entropy Oxides Featuring High H2‑production27. Using active learning to identify 14,000 high-entropy oxides, successfully screening 4 high-activity hydrogen evolution catalysts
Advancing refractory high entropy alloy development with AI-predictive models for high temperature oxidation resistance29. Gradient Boosting Decision Tree (GBDT) technology further improves high-precision prediction of high-entropy alloy oxidation resistance

AI+ Meteorology

Accurate Mediterranean Sea forecasting via graph-based deep learning13. Joint team proposes Graph Neural Network model SeaCast, achieving ultra-fast regional ocean forecasting
A new paradigm for medium-range severe weather forecasts: probabilistic random forest-based predictions4. Random Forest-based machine learning model CSU-MLP predicts medium-range severe weather
Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting10. Elucidated Rolling Diffusion Model (ERDM) released, solving long-term forecasting challenges and maintaining a lead over EDM baselines in medium-to-long term forecasts
End-to-end data-driven weather prediction5. End-to-end data-driven weather forecasting system Aardvark Weather speeds up predictions by dozens of times compared to traditional methods

AI+ Zoology-Botany

Accurate proteome-wide missense variant effect prediction with AlphaMissense4. AI camera alert system accurately distinguishes tigers from other species
Adaptive and maladaptive introgression in grapevine domestication8. Machine learning-based population genetics method reveals the formation mechanism of grape flavors
A deep learning approach to photo–identification demonstrates high performance on two dozen cetacean species6. Multi-species image recognition model based on ArcFace Classification Head for face recognition
BirdFlow: Learning seasonal bird movements from eBird data10. BirdFlow model accurately predicts flight paths of migratory birds
Cetacean dataset6. Multi-species image recognition model based on ArcFace Classification Head for face recognition
Contextual and combinatorial structure in sperm whale vocalisations12. Machine learning isolates the sperm whale phonetic alphabet, highly similar to human language with stronger information-carrying capacity

Others

Adaptive AI-based virtual reality sports system for adolescents with excess body weight: a randomized controlled trial25. World's first VR exercise intervention system REVERIE reshapes youth brain-body-mind health
AI-augmented photon-trapping spectrometer-on-a-chip on silicon platform with extended near-infrared sensitivity39. UC team proposes AI-augmented chip-scale spectrometer, achieving high spectral fidelity in an ultra-small volume
AI for Science: Intelligent scientific facilities revolutionize fundamental research3. Intelligent scientific facilities drive paradigm shifts in research
A neural network model to optimize the measure of spatial proximity in geographically weighted regression approach: a case study on house price in Wuhan15. Accurate prediction of Wuhan housing prices! osp-GNNWR model accurately describes complex spatial processes and geographical phenomena
An integrated microwave neural network for broadband computation and communication29. "Microwave Brain" chip born, simultaneously processing ultra-high-speed data and wireless signals with 75% accuracy at 176 milliwatts power
An open dataset for oracle bone script recognition and decipherment19. Containing 140,000 images! Oracle bone script dataset helps team win ACL Best Paper Award

AI+ Natural Disaster

A deep learning system for predicting time to progression of diabetic retinopathy2. Semantic segmentation model SCDUNet++ used for landslide mapping
Data-Driven Predictions of Peak Warming Under Rapid Decarbonization10. AI predicts global warming trends
Deep learning for cross-region streamflow and flood forecasting at a global scale7. ED-DLSTM achieves flood prediction in unmonitored areas
Enhanced forecasting of chlorophyll-a concentration in coastal waters through integration of Fourier analysis and Transformer networks8. ChloroFormer model provides early warning of marine algal blooms

AI+ Healthcare

A foundation model for generalizable disease detection from retinal images6. Retinal image foundation model RETFound predicts multiple systemic diseases
A high-performance neuroprosthesis for speech decoding and avatar control13. New AI brain-computer interface technology allows aphasic patients to "speak"
A multimodal multidomain multilingual medical foundation model for zero shot clinical diagnosis40. Medical model M³FM enables zero-shot clinical diagnosis, supporting disease reporting and classification
An interpretable model based on graph learning for diagnosis of Parkinson’s disease with voice-related EEG4. GSP-GCNs achieve up to 90.2% accuracy in Parkinson's disease diagnosis
Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study16. Ovarian cancer diagnostic AI fusion model MCF calculates risk using routine lab data and age
Artificial intelligence based multispecialty mortality prediction models for septic shock in a multicenter retrospective study54. Fusion strategy AI model predicts septic shock mortality risk

AI+ Astronomy

A Hybrid Spatiotemporal Fusion Method for High Spatial Resolution Imagery: Fusion of Gaofen-1 and Sentinel-2 over Agricultural Landscapes6. StarFusion model achieves high spatial resolution image prediction
AION-1: Omnimodal Foundation Model for Astronomical Sciences9. The first astronomical multimodal foundation model AION-1 is born, pre-trained on 200 million astronomical targets
An Algorithm for the Determination of Coronal Mass Ejection Kinematic Parameters Based on Machine Learning4. Machine learning-based method for CME identification and parameter extraction
Astronomaly at Scale: Searching for Anomalies Amongst 4 Million Galaxies3. Using unsupervised machine learning algorithm Astronomaly to find previously overlooked anomalies
Detecting rare neutral atomic-carbon absorbers with a deep neural network5. Deep learning discovers 107 cases of neutral carbon absorption lines
Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning8. Geospatial AI Earth AI focuses on 3 core data types, improving geospatial reasoning capabilities by 64%

Showing a sample of 648 resources. View the full list on GitHub →