SpaceManNabs's favorites

1.		Training LLMs to Reason in a Continuous Latent Space (arxiv.org)
		283 points by omarsar 26 days ago \| 114 comments
2.		Grifters, believers, grinders, and coasters (seangoedecke.com)
		232 points by rbanffy 32 days ago \| 118 comments
3.		Genie 2: A large-scale foundation world model (deepmind.google)
		1247 points by meetpateltech 32 days ago \| 410 comments
4.		Fraud, so much fraud (science.org)
		1528 points by nabla9 3 months ago \| 823 comments
5.		Synchronizing Pong to music with constrained optimization (victortao.substack.com)
		321 points by platers 4 months ago \| 37 comments
6.		Revisiting the Classics: Jensen's Inequality (2023) (francisbach.com)
		89 points by cpp_frog 4 months ago \| 8 comments
7.		Transformers in music recommendation (research.google)
		211 points by panarky 4 months ago \| 125 comments
8.		Seven basic rules for causal inference (pedermisager.org)
		218 points by RafelMri 4 months ago \| 67 comments
9.		Are Emergent Abilities in Large Language Models Just In-Context Learning? (arxiv.org)
		27 points by croes 4 months ago
10.		Does Reasoning Emerge? Probabilities of Causation in Large Language Models (arxiv.org)
		165 points by belter 4 months ago \| 192 comments
11.		Grokked Transformers Are Implicit Reasoners (arxiv.org)
		239 points by jasondavies 7 months ago \| 61 comments
12.		Show HN: I built a game to help you learn neural network architectures (sabrina.dev)
		321 points by sabrina_ramonov 7 months ago \| 62 comments
13.		TimesFM: Time Series Foundation Model for time-series forecasting (github.com/google-research)
		317 points by yeldarb 8 months ago \| 118 comments
14.		Deep Reinforcement Learning: Zero to Hero (github.com/alessiodm)
		535 points by alessiodm 8 months ago \| 47 comments
15.		Kolmogorov-Arnold Networks (github.com/kindxiaoming)
		568 points by sumo43 8 months ago \| 142 comments
16.		A Visual Guide to Vision Transformers (mdturp.ch)
		237 points by md2rp 8 months ago \| 26 comments
17.		Histograms for Probability Density Estimation: A Primer (vvanirudh.github.io)
		27 points by vvanirudh 9 months ago \| 12 comments
18.		Implementation of Google's Griffin Architecture – RNN LLM (github.com/google-deepmind)
		218 points by milliondreams 9 months ago \| 38 comments
19.		A generalist AI agent for 3D virtual environments (deepmind.google)
		559 points by nuz 9 months ago \| 310 comments
20.		Diffusion models from scratch, from a new theoretical perspective (chenyang.co)
		379 points by jxmorris12 10 months ago \| 40 comments
21.		What Is a Schur Decomposition? (2022) (nhigham.com)
		90 points by vector_spaces 10 months ago \| 27 comments
22.		Mamba: The Easy Way (jackcook.com)
		279 points by jackcook 10 months ago \| 60 comments
23.		Gemma: New Open Models (blog.google)
		1129 points by meetpateltech 10 months ago \| 509 comments
24.		The killer app of Gemini Pro 1.5 is using video as an input (simonwillison.net)
		1136 points by simonw 10 months ago \| 484 comments
25.		Stable Diffusion 3 (stability.ai)
		983 points by reqo 10 months ago \| 693 comments
26.		Training LLMs to generate text with citations via fine-grained rewards (arxiv.org)
		170 points by PaulHoule 10 months ago \| 34 comments
27.		Sora: Creating video from text (openai.com)
		3647 points by davidbarker 10 months ago \| 2231 comments
28.		Higher Order Derivatives of Transforms (nosferalatu.com)
		87 points by nosferalatu123 11 months ago \| 24 comments
29.		LLM in a Flash: Efficient LLM Inference with Limited Memory (huggingface.co)
		252 points by ghshephard on Dec 20, 2023 \| 53 comments
30.		VideoPoet A large language model for zero-shot video generation (research.google)
		126 points by fchyan on Dec 19, 2023 \| 40 comments
		More