Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason! By Writer and 1 other • 9 days ago • 55
mem-agent: Persistent, Human Readable Memory Agent Trained with Online RL By driaforall and 1 other • 9 days ago • 16
AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language Models By imomayiz and 4 others • 4 days ago • 10
"Anemll-style" Root-Mean-Square (RMS) Normalization on the Apple Neural Engine: A Simple Hack By anemll • 4 days ago • 9
🌎 What kind of environmental impacts are AI companies disclosing? (And can we compare them?) 🌎 By sasha and 1 other • 3 days ago • 7
Use AI on Your PC: Optimize and Deploy a Multimodal Agentic Pipeline on AI PC Powered by Intel By estellea and 2 others • 3 days ago • 5
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge By NormalUhr • Feb 7 • 218
🥬 TinyLettuce: Efficient Hallucination Detection with 17–68M Encoders By adaamko and 1 other • 20 days ago • 12
Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason! By Writer and 1 other • 9 days ago • 55
mem-agent: Persistent, Human Readable Memory Agent Trained with Online RL By driaforall and 1 other • 9 days ago • 16
AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language Models By imomayiz and 4 others • 4 days ago • 10
"Anemll-style" Root-Mean-Square (RMS) Normalization on the Apple Neural Engine: A Simple Hack By anemll • 4 days ago • 9
🌎 What kind of environmental impacts are AI companies disclosing? (And can we compare them?) 🌎 By sasha and 1 other • 3 days ago • 7
Use AI on Your PC: Optimize and Deploy a Multimodal Agentic Pipeline on AI PC Powered by Intel By estellea and 2 others • 3 days ago • 5
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge By NormalUhr • Feb 7 • 218
🥬 TinyLettuce: Efficient Hallucination Detection with 17–68M Encoders By adaamko and 1 other • 20 days ago • 12