A Coding Guide to Build a Complete Single Cell RNA Sequencing Analysis Pipeline Using Scanpy for Clustering Visualization and Cell Type Annotation
In this tutorial, we build a complete pipeline for single-cell RNA sequencing analysis using Scanpy. We start by installing the required libraries and loading the PBMC 3k dataset, then perform…
RAG with Hybrid Search: How Does Keyword Search Work?
, I’ve talked a lot about Reterival Augmented Generation (RAG). In particular, I’ve covered the basics of the RAG methodology, as well as a bunch of relevant concepts, like chunking,…
Quantum Diffusion Models: Score Reversal Is Not Free in Gaussian Dynamics
arXiv:2603.06488v1 Announce Type: cross Abstract: Diffusion-based generative modeling suggests reversing a noising semigroup by adding a score drift. For continuous-variable Gaussian Markov dynamics, complete positivity couples drift and diffusion at…
[2601.02751] Window-based Membership Inference Attacks Against Fine-tuned Large Language Models
[Submitted on 6 Jan 2026 (v1), last revised 5 Mar 2026 (this version, v2)] View a PDF of the paper titled Window-based Membership Inference Attacks Against Fine-tuned Large Language Models,…
Cross-species gene redesign leveraging ortholog information and generative modeling
Datasets constructionDevelopment of the OrthologTransformer model required large-scale, high-quality ortholog datasets to accurately capture diverse genetic variations, including synonymous and non-synonymous substitutions, as well as insertions and deletions (indels). A…
AI maps the hidden forces shaping cancer survival worldwide
For the first time, scientists have applied machine learning, a form of artificial intelligence (AI), to identify the factors most closely linked to cancer survival in nearly every country across…
165,000 dementia patients reveal hidden stroke risk from common drug
A large UK study involving more than 165,000 people with dementia has found that the drug risperidone is linked to a higher risk of stroke in all groups of patients.…
Breakthrough optical processor lets AI compute at the speed of light
Modern artificial intelligence (AI) systems, from robotic surgery to high-frequency trading, rely on processing streams of raw data in real time. Extracting important features quickly is critical, but conventional digital…
Pushing the Boundaries of Arabic Language AI with Hybrid Architecture
Discover more in our official blogpost, featuring an interactive experience The journey of building world-class Arabic language models has been one of continuous learning and iteration. Today, we're excited to…
Speeding Up Variable-Length Training with Dynamic Context Parallelism and NVIDIA Megatron Core
This post introduces Dynamic Context Parallelism (Dynamic-CP), a scheduling approach in NVIDIA Megatron Core used for LLM post-training or DiT pre-training. It dynamically selects the CP size per microbatch to…