Submissions from huggingface.co

		Show HN: Image to Explorable 3D Scene (huggingface.co)
		2 points by ggamecrazy 3 hours ago \| past \| discuss
		Building a Fast Multilingual OCR Model with Synthetic Data (huggingface.co)
		2 points by gmays 3 hours ago \| past \| discuss
		We OCR'ed 30k papers using Codex, open OCR models and Jobs (huggingface.co)
		3 points by speckx 6 hours ago \| past \| discuss
		5.6x throughput on Kimi K2.6 by speculating less (huggingface.co)
		9 points by florianleibert 9 hours ago \| past \| 2 comments
		Granite-4.0-Tiny-Preview (huggingface.co)
		1 point by handfuloflight 10 hours ago \| past \| discuss
		Kimi K2.6 (huggingface.co)
		11 points by kbumsik 1 day 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 1 day ago \| past \| discuss
		Show HN: Overlapping Speaker Transcription Model (huggingface.co)
		1 point by mcgov 1 day ago \| past \| discuss
		Qwen releases Qwen3-Embedding-0.6B (huggingface.co)
		4 points by arabicalories 1 day ago \| past \| 2 comments
		Why do language models feel worse even as benchmarks improve? [pdf] (huggingface.co)
		2 points by scaledsystems 1 day ago \| past \| discuss
		How to Fine-Tune a Reasoning Model? (huggingface.co)
		1 point by Anon84 3 days ago \| past \| discuss
		Parsebench open leaderboard for PDF parsing (huggingface.co)
		1 point by pierre 4 days ago \| past \| discuss
		Vakra: Reasoning, Tool Use, and Failure Modes of Agents (huggingface.co)
		2 points by gmays 4 days ago \| past \| discuss
		Alibaba open-sources Qwen3.6-35B-A3B, a 35B MoE model with 3B active parameters (huggingface.co)
		9 points by steveharing1 5 days ago \| past \| discuss
		Bonsai 1.7B in the browser: a 290MB 1-bit LLM on WebGPU (huggingface.co)
		8 points by victormustar 5 days ago \| past \| discuss
		HuggingFace launches pre-compiled machine learning kernels repository (huggingface.co)
		3 points by embedding-shape 6 days ago \| past \| 2 comments
		Gemopus: A Gemma fine-tune that prioritizes stability over long chain-of-thought (huggingface.co)
		1 point by steveharing1 7 days ago \| past \| discuss
		Kernels (huggingface.co)
		1 point by tosh 7 days ago \| past \| discuss
		Neo-Unify: An Encoder-Free, Native Multimodal Paradigm (SenseTime) (huggingface.co)
		3 points by WayLonWen 7 days ago \| past \| discuss
		Multimodal Embedding and Reranker Models with Sentence Transformers (huggingface.co)
		1 point by gmays 7 days ago \| past \| discuss
		HuggingFace Papers (huggingface.co)
		2 points by pierre 7 days ago \| past \| discuss
		ALTK‑Evolve: On‑the‑Job Learning for AI Agents (huggingface.co)
		1 point by gmays 8 days ago \| past \| discuss
		Show HN: NRC nuclear licensing RAG pipeline and regulatory embeddings dataset (huggingface.co)
		2 points by davenporten 8 days ago \| past \| discuss
		Is Your AI Coding Agent Being Watched While Benchmarked:Hidden Logging? (huggingface.co)
		2 points by NedimRenesalis 8 days ago \| past \| discuss
		"Darwin-27B-Opus: Surpassing the Foundation Model Without Training" (huggingface.co)
		3 points by makaimc 8 days ago \| past \| discuss
		Distilling 100B+ Models 40x Faster with TRL (huggingface.co)
		13 points by kashifr 8 days ago \| past \| discuss
		Minimax M2.7 Weights Released (huggingface.co)
		11 points by anonym29 9 days ago \| past \| 5 comments
		Show HN: MoodSense AI – mood detection and recommendations from text (huggingface.co)
		2 points by aman179102 10 days ago \| past \| discuss
		A long-term memory system that turns agent trajectories into reusable guidelines (huggingface.co)
		4 points by allthingsapi 10 days ago \| past \| 1 comment
		Raon-SpeechChat-9B: A Full-Duplex Speech Language Model (huggingface.co)
		2 points by BrutalCoding 11 days ago \| past \| discuss
		More

HN For You