Submissions from huggingface.co

		Building a Fast Multilingual OCR Model with Synthetic Data (huggingface.co)
		3 points by ibobev 16 hours ago \| past \| discuss
		DeepSeek-V4: a million-token context that agents can use (huggingface.co)
		12 points by ibobev 16 hours ago \| past \| discuss
		Adaptive Ultrasound Imaging with Physics (huggingface.co)
		2 points by ibobev 16 hours ago \| past \| discuss
		How to Use Transformers.js in a Chrome Extension (huggingface.co)
		1 point by mariuz 23 hours ago \| past \| discuss
		Xiaomi open-sources MiMo-V2.5: 311B A15B 1M-context omnimodal model (huggingface.co)
		5 points by gainsurier 1 day ago \| past \| discuss
		Xiaomi MiMo-v2.5-Pro Open-Sourced: 1T Parameter Model (huggingface.co)
		9 points by gainsurier 1 day ago \| past \| 3 comments
		XiaomiMiMo/MiMo-v2.5 (huggingface.co)
		3 points by Philpax 1 day ago \| past \| discuss
		Live Demo: SRT adds transparency to Qwen black box (0.19%) (huggingface.co)
		2 points by spacebacon 1 day ago \| past \| discuss
		Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond (huggingface.co)
		1 point by matrix-agent 1 day ago \| past \| discuss
		First DeepSeek V4 Flash-Base-Int4 Quant (huggingface.co)
		5 points by saivegasena 1 day ago \| past \| 3 comments
		Show HN: SRT-Adapter: 0.99 AUROC, perplexity win and 16.7× recall (0.19%) (huggingface.co)
		2 points by spacebacon 2 days ago \| past \| discuss
		DeepSeek V4 Flash (huggingface.co)
		14 points by S0y 5 days ago \| past \| discuss
		DeepSeek-V4 (huggingface.co)
		7 points by meetpateltech 5 days ago \| past \| discuss
		[dupe] DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence (huggingface.co)
		159 points by cmrdporcupine 5 days ago \| past \| 19 comments
		DeepSeek-V4 Technical Report [pdf] (huggingface.co)
		26 points by tianyicui 5 days ago \| past \| 4 comments
		OpenAI Privacy Filter (huggingface.co)
		4 points by handfuloflight 6 days ago \| past \| discuss
		The PR you would have opened yourself (huggingface.co)
		2 points by gmays 6 days ago \| past \| discuss
		Qwen/Qwen3.6-27B · Hugging Face (huggingface.co)
		41 points by cgeier 6 days ago \| past \| 6 comments
		Show HN: Image to Explorable 3D Scene (huggingface.co)
		2 points by ggamecrazy 7 days ago \| past \| discuss
		Building a Fast Multilingual OCR Model with Synthetic Data (huggingface.co)
		3 points by gmays 7 days ago \| past \| discuss
		We OCR'ed 30k papers using Codex, open OCR models and Jobs (huggingface.co)
		7 points by speckx 7 days ago \| past \| discuss
		5.6x throughput on Kimi K2.6 by speculating less (huggingface.co)
		11 points by florianleibert 7 days ago \| past \| 2 comments
		Granite-4.0-Tiny-Preview (huggingface.co)
		1 point by handfuloflight 7 days ago \| past \| discuss
		Kimi K2.6 (huggingface.co)
		11 points by kbumsik 8 days ago \| past \| 1 comment
		Show HN: We trained a 32B model to beat Opus 4 at credit card optimization (huggingface.co)
		6 points by dimberman 8 days ago \| past \| discuss
		Show HN: Overlapping Speaker Transcription Model (huggingface.co)
		1 point by mcgov 8 days ago \| past \| discuss
		Qwen releases Qwen3-Embedding-0.6B (huggingface.co)
		4 points by arabicalories 9 days ago \| past \| 3 comments
		Why do language models feel worse even as benchmarks improve? [pdf] (huggingface.co)
		2 points by scaledsystems 9 days ago \| past \| discuss
		How to Fine-Tune a Reasoning Model? (huggingface.co)
		1 point by Anon84 10 days ago \| past \| discuss
		Parsebench open leaderboard for PDF parsing (huggingface.co)
		1 point by pierre 11 days ago \| past \| discuss
		More