Submissions from huggingface.co

		Improve Accuracy in Multimodal Search and Visual Document Retrieval (huggingface.co)
		1 point by ibobev 15 days ago \| past
		Nvidia AI Released Nemotron Speech ASR (huggingface.co)
		2 points by nathan_tarbert 15 days ago \| past
		Show HN: 30k IKEA items in flat text (huggingface.co)
		55 points by tsazan 15 days ago \| past \| 34 comments
		Diversity Vs Density: A data strategy comparison for fine-tuning VLMs (huggingface.co)
		2 points by silvervein 16 days ago \| past \| 1 comment
		Alpie Core: a 32B reasoning model trained and served at 4-bit (huggingface.co)
		2 points by ChiragArya 16 days ago \| past \| 2 comments
		Show HN: Dowser – Training Data Recommendation System (huggingface.co)
		2 points by zrmarine 16 days ago \| past
		Nvidia/nemotron-speech-streaming-en-0.6B (huggingface.co)
		2 points by tilt 16 days ago \| past
		Nvidia brings agents to life with DGX Spark and Reachy Mini (huggingface.co)
		3 points by ibobev 16 days ago \| past
		Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI (huggingface.co)
		3 points by ibobev 16 days ago \| past
		Nvidia Cosmos Reason 2 Brings Advanced Reasoning to Physical AI (huggingface.co)
		2 points by ibobev 16 days ago \| past \| 1 comment
		Tflops Gap: Why FP4 Moe Kernel Engineering Matters on Blackwell (huggingface.co)
		1 point by apsys 17 days ago \| past
		Falcon H1R 7B (huggingface.co)
		2 points by ibobev 17 days ago \| past
		Meta releases open data to train General AI Co-Scientists (huggingface.co)
		1 point by shash42 18 days ago \| past
		Anatomy of BoltzGen (huggingface.co)
		31 points by danielfalbo 19 days ago \| past \| 1 comment
		Red Teaming with RL: Exploiting Tinker API for Harmful RL on 235B Model (huggingface.co)
		2 points by gmays 20 days ago \| past
		I Accidentally Rebuilt OpenHands from Scratch – Here's What I Learned (huggingface.co)
		2 points by couAUIA 21 days ago \| past
		DeepSeek MHC: Manifold-Constrained Hyper-Connections (huggingface.co)
		4 points by marc__1 21 days ago \| past
		Show HN: Open Schematics – Largest Hardware Schematic Dataset (huggingface.co)
		4 points by hn_way 22 days ago \| past
		The Optimal Architecture for Small Language Models (huggingface.co)
		2 points by simonpure 25 days ago \| past
		Aligning to What? Rethinking Agent Generalization in MiniMax M2 (huggingface.co)
		2 points by victormustar 27 days ago \| past
		The Optimal Architecture for Small Language Models (huggingface.co)
		1 point by codelion 28 days ago \| past
		A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems (huggingface.co)
		1 point by ibobev 30 days ago \| past
		Maincoder-1B – an open 1B-parameter coding model with 76% HumanEval (huggingface.co)
		4 points by MainNews 30 days ago \| past \| 3 comments
		DataFlow: Using LLMs to Build Reproducible, End-to-End Data Pipelines (huggingface.co)
		2 points by Mey0320 31 days ago \| past \| 1 comment
		Reachy Mini – A Hugging Face Space by Pollen-Robotics (huggingface.co)
		1 point by ulrischa 31 days ago \| past
		Speech to text model for healthcare-based voice applications (huggingface.co)
		3 points by tzury 33 days ago \| past
		NitroGen: Unified vision-to-action model designed to play video games (huggingface.co)
		4 points by intelkishan 33 days ago \| past
		Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition (huggingface.co)
		3 points by mattnewton 34 days ago \| past
		Show HN: Open-Source Browser Use LLM (30B, A3B) (huggingface.co)
		2 points by gregpr07 34 days ago \| past
		Surf Spot Finder (huggingface.co)
		1 point by geox 34 days ago \| past
		More