Submissions from huggingface.co

		MLA: K/V cache compression with low-rank projection (huggingface.co)
		1 point by samber 22 hours ago \| past \| discuss
		Benchmark for Evaluating Text Embeddings (huggingface.co)
		2 points by fzliu 1 day ago \| past \| discuss
		Better than DeepSeek R1? MiniMax-M1:open-weight hybrid-attention reasoning model (huggingface.co)
		4 points by helloericsf 1 day ago \| past \| discuss
		Nanonets-OCR-s – OCR model that transforms documents into structured markdown (huggingface.co)
		351 points by PixelPanda 2 days ago \| past \| 77 comments
		Embedding Benchmark for Retrieval (huggingface.co)
		1 point by fzliu 4 days ago \| past \| discuss
		Saying Thank You to a LLM Isn't Free – Measuring the Energy Cost of Politeness (huggingface.co)
		1 point by atlasunshrugged 4 days ago \| past \| 2 comments
		Zedge (ZDGE) releases foundational fully-licensed and segmented image dataset (huggingface.co)
		1 point by freemanlewin 5 days ago \| past \| 1 comment
		Show HN: ChatToSTL – AI text-to-CAD for 3D printing (huggingface.co)
		52 points by flowful 5 days ago \| past \| 6 comments
		Embedding Benchmark for Retrieval (huggingface.co)
		2 points by fzliu 7 days ago \| past \| discuss
		Show HN: Hugging Face Sheets – Excel meets unstructured data and open LLMs (huggingface.co)
		1 point by dvilasuero 7 days ago \| past \| discuss
		MiniCPM4 – a series of open multimodal models for edge inference (huggingface.co)
		2 points by cpldcpu 7 days ago \| past \| discuss
		Qwen3 Embedding Models (huggingface.co)
		1 point by kaycebasques 8 days ago \| past \| discuss
		Retrieval Embedding Benchmark (huggingface.co)
		1 point by fzliu 9 days ago \| past \| discuss
		Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design (huggingface.co)
		1 point by heyitsguay 10 days ago \| past \| discuss
		Understanding MCP Evals: Why Evals Matter for MCP (huggingface.co)
		3 points by mooreds 11 days ago \| past \| discuss
		The Common Pile v0.1 (huggingface.co)
		5 points by anigbrowl 11 days ago \| past \| discuss
		Watermarking Degrades Alignment in Language Models (ICLR GenAI Workshop 2025) (huggingface.co)
		1 point by dapurv5 11 days ago \| past \| 1 comment
		The Qwen3 Embedding Model (huggingface.co)
		2 points by sadaqabdo 12 days ago \| past \| discuss
		LeRobot Worldwide Hackathon (huggingface.co)
		1 point by cmatthieu 13 days ago \| past \| 1 comment
		Yambda-5B – Industrial-scale music recommendation dataset (huggingface.co)
		3 points by tazjin 13 days ago \| past \| 1 comment
		Show HN: Ego-Dex Gradio App (huggingface.co)
		3 points by pablovelagomez 14 days ago \| past
		Retrieval Embedding Benchmark (huggingface.co)
		2 points by fzliu 14 days ago \| past
		Show HN: Gemma 3 1B fine-tuned for Arabic Grammatical Error Correction (huggingface.co)
		1 point by bahjat 15 days ago \| past
		Show HN: Penny-1.7B Irish Penny Journal style transfer (huggingface.co)
		149 points by deepsquirrelnet 15 days ago \| past \| 76 comments
		TiRex Leads Gift Eval (huggingface.co)
		2 points by BobWue 15 days ago \| past \| 1 comment
		DeepSeek-R1-0528 performance improvements (huggingface.co)
		14 points by pama 19 days ago \| past \| 3 comments
		SOTA Model in 8B Size? (huggingface.co)
		2 points by ConteMascetti71 19 days ago \| past \| 2 comments
		SWE-rebench: Over 21,000 Open Tasks for SWE LLMs (huggingface.co)
		5 points by ibragim_bad 19 days ago \| past \| 1 comment
		Deepseek R1-0528 (huggingface.co)
		451 points by error404x 20 days ago \| past \| 250 comments
		Yambda-5B – a large-scale multi-modal dataset for ranking and retrieval (huggingface.co)
		2 points by zhisme 20 days ago \| past
		More