What a self-inflicted wound by the GOP… Just release the files, deal with a bit of embarrassment and get back to the Trump 2.0 agenda — which the 47th administration has completely ignored for months. This is the challenge with 47 — focusing on what matters to the people who…
阿里的Qwen3-VL能本地跑了，已上架llama.cpp 现在可以在个人设备上直接运行了，支持CPU、CUDA、Metal、Vulkan等 从2B到235B的GGUF权重也都已发布 #Qwen3VL
🎉 Qwen3-VL is now available on llama.cpp! Run this powerful vision-language model directly on your personal devices—fully supported on CPU, CUDA, Metal, Vulkan, and other backends. We’ve also released GGUF weights for all variants—from 2B up to 235B. Download and enjoy! 🚀 🤗…
Oxytocin modulates respiratory heart rate variability through a hypothalamus–brainstem–heart neuronal pathway nature.com/articles/s4159…
复刻Manus，无需邀请码，开源版Manus！ 支持在电脑上完成很多任务，包括网页浏览、文件操作、写代码等 OpenManus使用了传统的ReAct模式，优势是基于当前的状态进行决策，上下文和记忆方便管理，无需单独处理，需要注意，Manus有使用Plan进行规划 OpenManus目前也已初步加入了具有…
Tried ChatGPT’s advanced audio/video mode with pathology content—impressive! 📱 Pointed my phone at the screen showing a teaching slide, asked questions, and it nailed it. This could revolutionize how students learn pathology. Check it out!
Multimodal RAG, visually explained! Vanilla RAG systems work well on text documents. But real-world documents contain text + images + tables, and whatnot. Handling such multimodal data introduces additional challenges in parsing, embedding, and retrieval. Multimodal RAG…
Announcing new open-source Python package: aisuite! This makes it easy for developers to use large language models from multiple providers. When building applications I found it a hassle to integrate with multiple providers. Aisuite lets you pick a "provider:model" just by…
🎯 Fine-tuning Llama 3.2 Vision Model for Medical Imaging 📚 Hands-on Tutorial Section 📥 AI In Healthcare 🔑 How to Train Model with Images? 📈 How to Train 2x faster? 🗃️ How to Prepare Dataset? 💾 How to Save Fine-tuned Model? ☁️ How to Upload to @huggingface ? ⚙️ Using…
ChatGPT can now create Mind Maps. No more wasting hundreds of hours making visuals for studying or simplifying complex ideas. Here’s how to do it for free in a few seconds:
Microsoft Magentic AI Agents with @ollama 100% Local and Private 📚 Step-by-step Hands-on tutorial 🔧 How to Install? ⚙️ How to Configure? 🚀 How to Run? 🤖 What are Key Features? ⚠️ What are Current Limitations? @pyautogen @adamfourney
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: arxiv.org/pdf/2411.11922 - code: github.com/yangchris11/sa… - license: Apache-2.0
I turned ChatGPT into my personal assistant. Now I only work 1 hour a day. Here are 8 prompts I use to save hours every week:
Fashion-VDM can generate high-quality virtual try-on videos by combining an image of a garment with a video of a person! It maintains the person's identity and movement while ensuring clear details and smooth transitions in the video. johannakarras.github.io/Fashion-VDM
Wholesome AI use case: A teacher made images for her students of their future selves in their dream jobs
tomorrow, I'll be hosting a talk for @MIT; I'll be speaking about open-source computer vision tools 12:00 PM PST / 03:00 PM EST / 09:00 PM CET we'll be streaming on X: x.com/i/broadcasts/1…
M4 Mac Mini AI Cluster Uses @exolabs with Thunderbolt 5 interconnect (80Gbps) to run LLMs distributed across 4 M4 Pro Mac Minis. The cluster is small (iPhone for reference). It’s running Nemotron 70B at 8 tok/sec and scales to Llama 405B (benchmarks soon).
Mastering Time Management:
United States Trends
- 1. Texas A&M 13.3K posts
- 2. South Carolina 13.1K posts
- 3. Marcel Reed 2,611 posts
- 4. Aggies 3,836 posts
- 5. Nyck Harbor 1,419 posts
- 6. College Station 2,038 posts
- 7. Elko 2,418 posts
- 8. Jeremiyah Love 3,250 posts
- 9. Malachi Fields 1,396 posts
- 10. Mike Shula N/A
- 11. Dylan Stewart N/A
- 12. Shane Beamer N/A
- 13. TAMU 5,707 posts
- 14. Sellers 9,605 posts
- 15. #GoIrish 2,990 posts
- 16. Michigan 39.5K posts
- 17. Northwestern 4,220 posts
- 18. Zvada N/A
- 19. Randy Bond N/A
- 20. Sherrone Moore N/A
Something went wrong.
Something went wrong.