Targeting immune hubs to advance cancer immunotherapy | Science Translational Medicine ⁦Gladstone Institutes⁩ ⁦Parker Institute for Cancer Immunotherapy⁩ ⁦UCSF School of Medicine⁩ science.org/doi/10.1126/sc…

Anthropic just dropped the beautiful explaination of how they built a multi-agent research system using multiple Claude AI agents. A MUST read for anyone building multi-agent system. A lead agent plans research steps, spawns specialized subagents to search in parallel, and

Microsoft dropped a free AI Agent training for beginners. No paywall. No coding required. This could change how millions learn AI. Here’s what’s inside ↓

Even the smartest LLMs can fail at basic multiturn communication Ask for grocery help → without asking where you live 🤦‍♀️ Ask to write articles → assumes your preferences 🤷🏻‍♀️ ⭐️CollabLLM (top 1%; oral ICML Conference) transforms LLMs from passive responders into active collaborators.

🚀 Xaira Therapeutics has just dropped a game-changer for AI-driven biology. Today, we unveiled X-Atlas/Orion, the largest publicly available genome-wide Perturb-seq dataset to date—spanning 8.4 million single cells with perturbations across all ~20,000 human protein-coding

Proud to introduce TIME_ACT: an unsupervised, #pancancer signature, which accurately identifies hot tumors and predicts response to #ICB across #Cancer from tumor transcriptomics and histopathology. 🧵 (1/6) 📄 doi.org/10.1101/2025.0…

I'm thrilled to share our new study out in Nature Medicine! We show that a blood test can estimate how aged or youthful one’s organs are and that these organ ages predict future disease and lifespan. Final paper from my PhD in the Tony Wyss-Coray lab. 🧵1/12 🔗 nature.com/articles/s4159…

Tumor neutrophils rewired from birth dlvr.it/TLyyhp

I still believe this is the best repo to learn about ai agents HANDS ON. it focuses on key applications, from basic to advanced and covers MCP, RAG, multi-agents and so much more. if you want to learn by coding (and you hate books) this is the way. 51K stars on GitHub! ✨

what are large language models actually doing? i read the 2025 textbook "Foundations of Large Language Models" by tong xiao and jingbo zhu and for the first time, i truly understood how they work. here’s everything you need to know about llms in 3 minutes↓

Towards Robust Foundation Models for Digital Pathology 1. This study investigates the robustness of biomedical foundation models (FMs) in digital pathology, revealing that current models are highly susceptible to non-biological technical variations such as staining differences

A CXCR4 partial agonist improves immunotherapy by targeting immunosuppressive neutrophils and cancer-driven granulopoiesis dlvr.it/TMS1Mc

This one paper might kill the LLM agent hype. NVIDIA just published a blueprint for agentic AI powered by Small Language Models. And it makes a scary amount of sense. Here’s the full breakdown:

Some interesting Nano Banana/Gemini 2.5 Flash Image use cases 👇🧵

🚨BREAKING: Microsoft just dropped Copilot integration and it's INSANE Your ultimate assistant for PowerPoint, Excel, Teams, Outlook, and Word. Here are 10 powerful features you can't afford to miss:

This is the most detailed view of a human brain to date. This sample is only ~3 mm wide.

Knowledge is like an ocean, vast and infinite. The further you venture, the deeper you realize it goes. Yet, if you only stand at the shore, you may falsely believe you've seen its entirety.

Just published in Nature Communications! 🚨 We tracked #immune cell changes in blood during anti-PD-1 treatment and identified a non-invasive, early on-treatment biomarker of #immunotherapy response in #headandneck #Cancer. 🧵(1/5) 📜 doi.org/10.1038/s41467…

Everyone is talking about this new OpenAI paper. It's about why LLMs hallucinate. You might want to bookmark this one. Let's break down the technical details:

Somebody wrote a prompt that's supposed to reduce ChatGPT hallucinations. A Reality Filter Has a Google Gemini and Claude version too. it’s a directive scaffold that makes them more likely to admit when they don’t know. "Reduce hallucinations mechanically—through repeated