panabee's submissions

1.		DiLoCo: Distributed Low-Communication Training of Language Models (huggingface.co)
		3 points by panabee 75 days ago \| past
2.		Revised Chinchilla scaling laws – LLM compute and token requirements (educatingsilicon.com)
		1 point by panabee 81 days ago \| past
3.		Compute-Optimal Context Size (manifestai.com)
		3 points by panabee 3 months ago \| past
4.		An Empirical Study of Mamba-Based Language Models (arxiv.org)
		43 points by panabee 3 months ago \| past \| 3 comments
5.		Human Language Understanding and Reasoning (2022) (amacad.org)
		1 point by panabee 4 months ago \| past
6.		MapReduce: A Flexible Data Processing Tool (2010) (acm.org)
		3 points by panabee 4 months ago \| past \| 1 comment
7.		RLHF: Reinforcement Learning from Human Feedback (huyenchip.com)
		1 point by panabee 4 months ago \| past
8.		Gemini 1.5 Model Family: Technical Report [pdf] (storage.googleapis.com)
		57 points by panabee 4 months ago \| past \| 3 comments
9.		Illuminate: Turn academic papers into AI-generated audio discussions (withgoogle.com)
		3 points by panabee 4 months ago \| past \| 1 comment
10.		Sparse Llama: 70% Smaller, 3x Faster, Full Accuracy (cerebras.net)
		40 points by panabee 4 months ago \| past \| 1 comment
11.		Mitochondria and Chloroplasts (khanacademy.org)
		2 points by panabee 5 months ago \| past
12.		Asian American women are getting lung cancer despite never smoking (nbcnews.com)
		148 points by panabee 5 months ago \| past \| 146 comments
13.		CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data (arxiv.org)
		48 points by panabee 5 months ago \| past \| 4 comments
14.		Patchscopes: A framework for viewing hidden representations of language models (research.google)
		12 points by panabee 5 months ago \| past
15.		Understanding Diffusion Models: A Unified Perspective (arxiv.org)
		2 points by panabee 6 months ago \| past
16.		Fast-forward – comparing a 1980s supercomputer to the modern smartphone (adobe.com)
		2 points by panabee 6 months ago \| past
17.		Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient LMs (arxiv.org)
		1 point by panabee 6 months ago \| past
18.		Prostate cancer includes two different evotypes (ox.ac.uk)
		152 points by panabee 6 months ago \| past \| 84 comments
19.		Stanford researchers: 45% of GPT4 responses to medical queries hallucinate (twitter.com/james_y_zou)
		3 points by panabee 7 months ago \| past \| 4 comments
20.		Understanding Diffusion Models: A Unified Perspective (arxiv.org)
		3 points by panabee 8 months ago \| past
21.		The promises and pitfalls of specialized ribosomes (2022) (sciencedirect.com)
		2 points by panabee 9 months ago \| past
22.		Shallow Feed-Forward Neural Networks as Alternative to Attention in Transformers (huggingface.co)
		11 points by panabee 10 months ago \| past
23.		New Bing attracts new Edge users – who then use Google Search (searchengineland.com)
		2 points by panabee 10 months ago \| past
24.		FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores (stanford.edu)
		3 points by panabee 11 months ago \| past
25.		The core contribution of "Attention is All You Need" is logistic regressions (twitter.com/davidad)
		1 point by panabee 11 months ago \| past \| 1 comment
26.		'Anti-hunger' molecule forms after exercise, scientists discover (2022) (stanford.edu)
		1 point by panabee 11 months ago \| past
27.		LeanDojo: Theorem Proving with Retrieval-Augmented Language Models (leandojo.org)
		1 point by panabee 11 months ago \| past
28.		ConvNets Match Vision Transformers at Scale (huggingface.co)
		1 point by panabee 11 months ago \| past
29.		Fundamentals of Water Activity [pdf] (metergroup.com)
		2 points by panabee 12 months ago \| past \| 1 comment
30.		Llama Impact Grants (meta.com)
		4 points by panabee on Oct 7, 2023 \| past
		More