27 articles tagged with #scientific-computing. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have introduced Mozi, a dual-layer architecture designed to make AI agents more reliable for drug discovery by implementing governance controls and structured workflows. The system addresses critical issues of unconstrained tool use and poor long-term reliability that have limited LLM deployment in pharmaceutical research.
Researchers developed an end-to-end AI-based event reconstruction system for future particle colliders that uses geometric algebra transformer networks and object condensation clustering. The system outperforms traditional rule-based algorithms by 10-20% in reconstruction efficiency and improves energy resolution by 22%, while reducing fake-particle rates by up to two orders of magnitude.
Researchers have developed a Bayesian adversarial multi-agent framework for AI-driven scientific code generation, featuring three coordinated LLM agents that work together to improve reliability and reduce errors. The Low-code Platform (LCP) enables non-expert users to generate scientific code through natural language prompts, demonstrating superior performance in benchmark tests and Earth Science applications.
Researchers developed Physics-Embedded PINNs (PE-PINN) that achieve 10x faster convergence than standard physics-informed neural networks and orders of magnitude memory reduction compared to traditional methods for large-scale wave field reconstruction. The breakthrough enables high-fidelity electromagnetic wave modeling for wireless communications, sensing, and room acoustics applications.
Researchers have developed DynFormer, a new Transformer-based neural operator that improves partial differential equation (PDE) solving by incorporating physics-informed dynamics. The system achieves up to 95% reduction in relative error compared to existing methods while significantly reducing GPU memory consumption through specialized attention mechanisms for different physical scales.
Gemini 3 Deep Think represents an updated specialized reasoning mode designed to tackle complex challenges in modern science, research, and engineering. The advancement focuses on enhanced problem-solving capabilities for technical and scientific applications.
OpenAI has released GPT-5.2, their most advanced model for mathematics and science applications, achieving state-of-the-art performance on benchmarks like GPQA Diamond and FrontierMath. The model demonstrates significant research capabilities, including solving open theoretical problems and generating reliable mathematical proofs.
OpenAI is partnering with U.S. National Laboratories to deploy its latest reasoning AI models for scientific research and breakthroughs. This collaboration aims to strengthen America's artificial intelligence leadership by leveraging the nation's premier research institutions.
Researchers propose a sparse-aware neural network framework that combines convolutional architectures with fully connected networks to improve operator learning over infinite-dimensional function spaces. The approach significantly reduces the curse of dimensionality and sample complexity requirements for approximating nonlinear functionals, with improved theoretical guarantees for both deterministic and random sampling schemes.
CodeRefine is a new AI framework that automatically converts research paper methodologies into functional code using Large Language Models. The system creates knowledge graphs from papers and uses retrieval-augmented generation to produce more accurate code implementations than traditional zero-shot prompting methods.
The UK government has allocated £45 million to fund an AI supercomputer specifically designed to accelerate fusion power research and development. This investment represents a significant commitment to using advanced computing technology to solve one of the world's most challenging energy problems.
Researchers have developed improved Physics-Informed Neural Networks (PINNs) that significantly enhance accuracy in solving complex partial differential equations. The new adaptive loss balancing and residual-based collocation methods reduce errors by 44% for Burgers' equations and 70% for Allen-Cahn equations compared to traditional PINNs.
Researchers developed a data-free Physics-Informed Neural Network (PINN) that can solve compressible flows around circular cylinders at extreme speeds up to Mach 15. The system uses hybrid convolutions and Mach-guided scaling to overcome traditional limitations and successfully captures shock waves without requiring training data.
Researchers developed a training-efficient method to convert pre-trained deterministic AI models for solving Partial Differential Equations into probabilistic ones using Continuous Ranked Probability Score (CRPS) retrofitting. The approach achieves 20-54% improvements in accuracy metrics while requiring minimal additional training costs compared to retraining models from scratch.
Researchers have developed Re4, a multi-agent AI framework that uses three specialized LLMs (Consultant, Reviewer, and Programmer) working collaboratively to solve scientific computing problems. The system employs a rewriting-resolution-review-revision process that significantly improves bug-free code generation and reduces non-physical solutions in mathematical and scientific reasoning tasks.
Researchers introduce DataMind, a new training framework for building open-source data-analytic AI agents that can handle complex, multi-step data analysis tasks. The DataMind-14B model achieves state-of-the-art performance with 71.16% average score, outperforming proprietary models like DeepSeek-V3.1 and GPT-5 on data analysis benchmarks.
Research reveals that machine-learned operators (MLOs) fail at zero-shot super-resolution, unable to accurately perform inference at resolutions different from their training data. The study identifies key limitations in frequency extrapolation and resolution interpolation, proposing a multi-resolution training protocol as a solution.
Researchers published a case study demonstrating successful human-AI collaboration in mathematical research, extending Hermite quadrature rule results beyond manual capabilities. The study reveals AI's strengths in algebraic manipulation and proof exploration, while highlighting the critical need for human verification and domain expertise in every step of the research process.
AI engineer Laslo Hunhold has developed 'takums,' a new number format specifically designed for scientific computing that maintains dynamic range when using fewer bits. Unlike AI-optimized formats that work well for machine learning but fail in scientific applications, takums address the unique computational needs of physics, biology, and engineering simulations.
Quantum physicist Mario Krenn is utilizing OpenAI's o1 model to tackle fundamental questions in quantum physics. The collaboration demonstrates the potential for advanced AI systems to assist researchers in solving complex scientific problems.
This research review explores how artificial intelligence techniques can enhance Earth system modeling by improving coupling between physical, chemical, and biological processes across Earth's spheres. The study focuses on AI's potential to strengthen cross-domain interactions and create more unified Earth system frameworks beyond traditional climate models.
Aitomia is an AI-powered platform that assists researchers in performing atomistic and quantum chemical simulations through chatbots and AI agents. The platform combines LLM-based technology with the MLatom platform to support both AI-driven and conventional quantum-chemical calculations, democratizing access to complex computational workflows.
Researchers propose iMOOE, a physics-guided invariant learning method for forecasting partial differential equations (PDEs) dynamics with improved zero-shot generalization. The method addresses limitations in existing deep learning approaches that require test-time adaptation by incorporating fundamental physical invariance principles.
Researchers have extended the CNF framework to solve multi-variable and non-linear partial differential equations, addressing computational challenges in scientific simulations. The work focuses on improving PDE solvers for forward solutions, inverse problems, and equation discovery with self-tuning techniques and benchmark evaluations.
NuBench is a new open benchmark for deep learning-based event reconstruction in neutrino telescopes, comprising seven large-scale simulated datasets with nearly 130 million neutrino interactions. The benchmark enables comparison of machine learning reconstruction methods across different detector geometries and evaluates four algorithms including ParticleNeT and DynEdge on core reconstruction tasks.
