discuss:

Introducing 🥚EGGROLL 🥚(Evolution Guided General Optimization via Low-rank Learning)! 🚀 Scaling backprop-free Evolution Strategies (ES) for billion-parameter models at large population sizes ⚡100x Training Throughput 🎯Fast Convergence 🔢Pure Int8 Pretraining of RNN LLMs

Language Models are Provably Injective and Invertible! A groundbreaking paper challenges the long-held belief that LLMs lose information. They prove mathematically and show empirically across billions of tests that inputs map uniquely to representations, making them lossless.

🕳️🐇Into the Rabbit Hull – Part II Continuing our interpretation of DINOv2, the second part of our study concerns the geometry of concepts and the synthesis of our findings toward a new representational phenomenology: the Minkowski Representation Hypothesis

A graph-powered all-in-one RAG system! RAG-Anything is a graph-driven, all-in-one multimodal document processing RAG system built on LightRAG. It supports all content modalities within a single integrated framework. 100% open-source.

"Aggressive Filtering aint good for larger training" Similar find also at

🧠 How can AI evolve from statically 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘢𝘣𝘰𝘶𝘵 𝘪𝘮𝘢𝘨𝘦𝘴 → dynamically 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘪𝘮𝘢𝘨𝘦𝘴 as cognitive workspaces, similar to the human mental sketchpad? 🔍 What’s the 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗿𝗼𝗮𝗱𝗺𝗮𝗽 from tool-use → programmatic

UC Berkley has two free courses on LLM Agents for foundational and advanced levels. it also has some of the best lecturers from DeepMind, Meta, and top universities. basically covers all you need to know about agents from the best resources out there.

🤖Can diffusion models write code competitively? Excited to share our latest 7B coding diffusion LLM!!💻 With DiffuCoder, we explore how they decode, why temperature🔥 matters, and how to improve them via coupled-GRPO that speaks diffusion!!📈 Code: https://t.co/sWsb8a49HL 🧵

The Ultimate Toolkit for Working with LLMs! Transformer Lab lets you train, fine-tune, and chat with any LLM—100% locally. Enjoy 1-click LLM downloads and a drag-and-drop UI for RAG. 100% open-source.

LLMs running reinforcement learning shed their randomness almost at once, then their scores stall. This paper shows that randomness drop is predictable and fixable, so bigger gains are still on the table. The authors fit an exponential link between entropy and reward. Two

CVPR 2025 papers pt. 2 - SAMWISE SAMWISE adds language understanding and temporal reasoning to SAM2; you can segment and track objects in videos just by describing them more papers: https://t.co/1VlLn2BWxl ↓ more

Vision transformers have high-norm outliers that hurt performance and distort attention. While prior work removed them by retraining with “register” tokens, we find the mechanism behind outliers and make registers at ✨test-time✨—giving clean features and better performance! 🧵

I learnt a lot from O'Reilly books, this is surreal I'm writing a book with amazing people @micuelll @andimarafioti @orr_zohar about VLMs with @huggingface 📖💗 Early Access (first two chapters in raw) are available to everyone, we'd love to have your feedback!

🚀 Excited to share the most inspiring work I’ve been part of this year: "Learning to Reason without External Rewards" TL;DR: We show that LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence. 1/n

Here's Let's Build a Simple Database! It's a bit outdated, but it still perfectly covers the basics on how to get a sqlite clone going, in C. You'll learn a lot about databases and C, enjoy!

OpenMemory MCP provides a persistent memory layer for AI tools like Claude, Cursor and Windsurf. It enables AI Agents to securely read and write to a shared memory. Runs 100% locally on your computer.

A collection of awesome MCP servers for AI Agents:

🚨This week's top AI/ML research papers: - Absolute Zero - RM-R1 - Seed-Coder - Flow-GRPO - ZeroSearch - Ming-Lite-Uni - A Survey on Large Multimodal Reasoning Models - On Path to Multimodal Generalist - ZeroSearch - HunyuanCustom - Unified Multimodal CoT Reward Model through

The Ultimate Toolkit for Working with LLMs! Transformer Lab lets you train, fine-tune, and chat with any LLM—100% locally. Enjoy 1-click LLM downloads and a drag-and-drop UI for RAG. 100% open-source.