Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H
By
and 1 other
•
•
56
Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H
By
and 1 other
•
•
56*Context Is Gold to Find the Gold Passage*: Evaluating and Training Contextual Document Embeddings
By
and 1 other
•
•
22Uncensor any LLM with abliteration
By
•
•
603Explore, Build, and Innovate AI Reasoning with NVIDIA’s Open Models and Recipes
By
and 2 others
•
•
13Interactive Tools for machine learning, deep learning, and math
By
•
•
40AI Policy @🤗: Response to the 2025 National AI R&D Strategic Plan
By
and 2 others
•
•
12🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?
By
•
•
281System Prompt Learning: Teaching LLMs to Learn Problem-Solving Strategies from Experience
By
•
•
9Daily Robotics June #1 - SmolVLA discovery and thoughts
By
•
•
9xLSTM-based time series model TiRex significantly outperforms competing models in forecasting accuracy
By
•
•
9DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
147Bigger isn't always better: how to choose the most efficient model for context-specific tasks 🌱🧑🏼💻
By
•
•
18🌙 Introducing **Moon**: Storytelling Generator Model
By
and 1 other
•
•
6Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
By
•
•
328Common AI Model Formats
By
•
•
42PipelineRL
By
and 3 others
•
•
26Code a simple RAG from scratch
By
•
•
85Decoding Strategies in Large Language Models
By
•
•
66KV Caching Explained: Optimizing Transformer Inference Efficiency
By
•
•
72Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
By
•
•
17