
VibeGen uses agentic AI to design de novo proteins based on vibrational motion. This 2026 study reveals that diverse protein folds can share similar d...

Meta-Harness automated LLM harness optimization code improves text classification by 7.7 points and math reasoning by 4.7 points using filesystem acce...

TurboQuant online vector quantization distortion rate optimization achieves near-optimal results within a 2.7 factor of theoretical bounds. It ensures...

Researchers at Anthropic and Oxford identified a linear 'Assistant Axis' in LLM activation space that governs persona stability. Activation capping al...

A 2025 study used allele-specific CRISPR-Cas9 to eliminate the extra chromosome 21 from Down syndrome iPS cells, achieving a 30.6% karyotype correctio...

Repeating the input prompt improves accuracy across Gemini, GPT, Claude, and Deepseek models in 47 out of 70 benchmarks with zero losses and no added...

SleepFM, a foundation model trained on 585,000+ hours of sleep recordings, predicts 130 diseases from a single night's polysomnography with C-Index sc...

Gene-edited islet cells survived 12 weeks in a type 1 diabetes patient with zero immunosuppression drugs, using CRISPR-Cas12b to achieve 100% HLA-II d...

AlphaGenome is a new AI model from Google Deepmind team that analyzes massive 1-megabase chunks of DNA to predict how non-coding genetic regions funct...

Researchers created LLM-in-Sandbox, a framework that gives language models access to a virtual computer where they can execute commands, manage files,...

AlphaFold achieves atomic accuracy in protein structure prediction, transforming structural biology and bioinformatics.

Meta's VL-JEPA learns by predicting semantic embeddings instead of generating text token-by-token, allowing it to focus on meaning rather than phrasin...