WTF GENIUS PAPERS Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. Continuous Latent Diffusion Language Model Paper β’ 2605.06548 β’ Published 12 days ago β’ 76 Scaling Latent Reasoning via Looped Language Models Paper β’ 2510.25741 β’ Published Oct 29, 2025 β’ 229 Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper β’ 2502.05171 β’ Published Feb 7, 2025 β’ 155 Pretraining Language Models to Ponder in Continuous Space Paper β’ 2505.20674 β’ Published May 27, 2025 β’ 3
Scaling Latent Reasoning via Looped Language Models Paper β’ 2510.25741 β’ Published Oct 29, 2025 β’ 229
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper β’ 2502.05171 β’ Published Feb 7, 2025 β’ 155
Pretraining Language Models to Ponder in Continuous Space Paper β’ 2505.20674 β’ Published May 27, 2025 β’ 3
HUMAN-WRITTEN & LEGALLY-SOURCED* Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis *...mostly. BramVanroy/CommonCrawl-CreativeCommons Viewer β’ Updated Aug 28, 2025 β’ 739M β’ 7.79k β’ 34 PleIAs/common_corpus Viewer β’ Updated 13 days ago β’ 69.9k β’ 155k β’ 400 common-pile/comma_v0.1_training_dataset Viewer β’ Updated Jun 6, 2025 β’ 784M β’ 16.3k β’ 40 crumb/openstax-text Viewer β’ Updated Jul 14, 2023 β’ 3.35M β’ 2.05k β’ 5
WTF GENIUS PAPERS Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. Continuous Latent Diffusion Language Model Paper β’ 2605.06548 β’ Published 12 days ago β’ 76 Scaling Latent Reasoning via Looped Language Models Paper β’ 2510.25741 β’ Published Oct 29, 2025 β’ 229 Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper β’ 2502.05171 β’ Published Feb 7, 2025 β’ 155 Pretraining Language Models to Ponder in Continuous Space Paper β’ 2505.20674 β’ Published May 27, 2025 β’ 3
Scaling Latent Reasoning via Looped Language Models Paper β’ 2510.25741 β’ Published Oct 29, 2025 β’ 229
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper β’ 2502.05171 β’ Published Feb 7, 2025 β’ 155
Pretraining Language Models to Ponder in Continuous Space Paper β’ 2505.20674 β’ Published May 27, 2025 β’ 3
HUMAN-WRITTEN & LEGALLY-SOURCED* Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis *...mostly. BramVanroy/CommonCrawl-CreativeCommons Viewer β’ Updated Aug 28, 2025 β’ 739M β’ 7.79k β’ 34 PleIAs/common_corpus Viewer β’ Updated 13 days ago β’ 69.9k β’ 155k β’ 400 common-pile/comma_v0.1_training_dataset Viewer β’ Updated Jun 6, 2025 β’ 784M β’ 16.3k β’ 40 crumb/openstax-text Viewer β’ Updated Jul 14, 2023 β’ 3.35M β’ 2.05k β’ 5