Nirmaan: ML Research Forum

Welcome to Nirmaan, wanderer of weights and activations. Join the community to share papers, code, and AI debates with sharp minds worldwide and yes, to meme the machines. 🧠⚙️

Recent content by darkcyborg

  1. darkcyborg

    SSH AI CHAT - Cool projects

    ❇️ SSH AI Chat: Chat with AI over SSH 🔥🤖🔥 because who needs browsers when you have terminals? Ever wondered what happens when you mix SSH, minimalism, and large language models? Meet SSH AI Chat — an open-source project that lets you quite literally talk to an AI through your terminal. No...
  2. darkcyborg

    Youtu-LLM: Tiny Agent Beast - 4 Jan '26 ⚡

    🚀 Youtu-LLM: Lightweight Agentic LLM Powerhouse by Junru Lu, Jiarui Qin, Lingfeng Qiao et al. 💻 GitHub Repo: https://github.com/TencentCloudADP/youtu-tip 🔥 TLDR (Tiny Model, Giant Brain) Youtu-LLM is a 1.96B parameter beast that punches way above its weight class 💪. 🛠️ The Magic...
  3. darkcyborg

    Hypergraph RAG Drop, Jan 4 '26

    🧠 Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling by Chulun Zhou, Chunkang Zhang, Guoxin Yu, Fandong Meng, Jie Zhou, Wai Lam, Mo Yu 📄 Read Paper: https://huggingface.co/papers/2512.23959 TLDR (Too Long; Definitely Read 😏) 🚀 Enter...
  4. darkcyborg

    Gradient Descent - Good Reads

    Found this gem on gradient descent that actually explains why our models wobble at the "edge of stability" instead of politely staying put. Turns out we've been watching chaos with hidden order all along typical ML, making us feel smart and clueless simultaneously. The central flows framework...
Back
Top