| 1. | | Where is Noether's principle in machine learning? (cgad.ski) |
|
296 points by cgadski 8 months ago | 76 comments
|
|
| 2. | | The Era of 1-bit LLMs: ternary parameters for cost-effective computing (arxiv.org) |
|
1040 points by fgfm 8 months ago | 447 comments
|
|
| 3. | | Stop postponing things by embracing the mess (deprocrastination.co) |
|
359 points by vitabenes 9 months ago | 208 comments
|
|
| 4. | | Mamba: Linear-Time Sequence Modeling with Selective State Spaces (arxiv.org) |
|
130 points by anigbrowl 11 months ago | 37 comments
|
|
| 5. | | Bayesian Flow Networks (arxiv.org) |
|
122 points by albertzeyer on Aug 15, 2023 | 20 comments
|
|
| 6. | | Thermodynamic Linear Algebra (arxiv.org) |
|
234 points by aifer4 on Aug 13, 2023 | 55 comments
|
|
| 7. | | The Alexander Piano (alexanderpiano.nz) |
|
307 points by KolmogorovComp on Aug 7, 2023 | 102 comments
|
|
| 8. | | Functions are vectors (thenumb.at) |
|
432 points by TheNumbat on July 29, 2023 | 120 comments
|
|
| 9. | | People in 1920s Berlin nightclubs flirted via pneumatic tubes (2017) (atlasobscura.com) |
|
321 points by jakobdabo on July 24, 2023 | 125 comments
|
|
| 10. | | How the RWKV language model works (johanwind.github.io) |
|
71 points by EvgeniyZh on July 4, 2023 | 6 comments
|
|
| 11. | | Ask HN: What happened to fuzzy logic? |
|
107 points by _448 on May 25, 2023 | 75 comments
|
|
| 12. | | RWKV: Reinventing RNNs for the Transformer Era (arxiv.org) |
|
358 points by ianbutler on May 23, 2023 | 171 comments
|
|
| 13. | | Don Knuth plays with ChatGPT (stanford.edu) |
|
927 points by talonx on May 20, 2023 | 622 comments
|
|
| 14. | | GradIEEEnt half decent (tom7.org) |
|
275 points by notmysql_ on May 1, 2023 | 32 comments
|
|
| 15. | | The New XOR Problem (blog.wtf.sg) |
|
199 points by yeesian on April 18, 2023 | 87 comments
|
|
| 16. | | Generalizations of Fourier analysis (2021) (gabarro.org) |
|
130 points by mscharrer on April 15, 2023 | 26 comments
|
|
| 17. | | Algebraic graph calculus (2021) (gabarro.org) |
|
120 points by 082349872349872 on April 15, 2023 | 21 comments
|
|
| 18. | | Why Are Sinusoidal Functions Used for Position Encoding? (mfaizan.github.io) |
|
5 points by mfn on April 10, 2023 | 1 comment
|
|
| 19. | | From deep to long learning? (stanford.edu) |
|
499 points by headalgorithm on April 9, 2023 | 117 comments
|
|
| 20. | | Academic urban legends (2014) (sagepub.com) |
|
105 points by gammarator on March 6, 2023 | 63 comments
|
|
| 21. | | We Found an Neuron in GPT-2 (clementneo.com) |
|
431 points by todsacerdoti on Feb 16, 2023 | 169 comments
|
|
| 22. | | Just know stuff (or, how to achieve success in a machine learning PhD) (kidger.site) |
|
241 points by occamschainsaw on Jan 27, 2023 | 103 comments
|
|
| 23. | | Summer Afternoon – A WebGL Experiment (vlucendo.com) |
|
930 points by jaden on Jan 20, 2023 | 194 comments
|
|
| 24. | | Some Remarks on Large Language Models (gist.github.com) |
|
182 points by sherjilozair on Jan 3, 2023 | 79 comments
|
|
| 25. | | How does GPT obtain its ability? Tracing emergent abilities of language models (yaofu.notion.site) |
|
414 points by headalgorithm on Dec 14, 2022 | 192 comments
|
|
| 26. | | Show HN: We scaled Git to support 1 TB repos (xethub.com) |
|
279 points by reverius42 on Dec 13, 2022 | 144 comments
|
|
| 27. | | Show HN: Using Vim as an input method editor (IME) for X11 apps (github.com/algon-320) |
|
132 points by algon on Dec 4, 2022 | 27 comments
|
|
| 28. | | The essence of Reed-Solomon coding (mazzo.li) |
|
168 points by rostayob on Nov 6, 2022 | 41 comments
|
|
| 29. | | The Art of Command Line (github.com/jlevy) |
|
426 points by tambourine_man on Nov 24, 2022 | 80 comments
|
|
| 30. | | A Short Chronology of Deep Learning for Tabular Data (sebastianraschka.com) |
|
148 points by tosh on Sept 4, 2022 | 14 comments
|
|
|
|
More |
