|
|
|
Stories from September 20, 2023 (UTC)
|
| 1. |
Neurons in Large Language Models: Dead, N-Gram, Positional (arxiv.org) |
|
106 points by PaulHoule on Sep 20, 2023 | hide | past | pdf | 52 comments
|
|
| 2. |
Language Modeling Is Compression (arxiv.org) |
|
5 points by alphabetting on Sep 20, 2023 | hide | past | pdf | discuss
|
|
| 3. |
Adapting Large Language Models via Reading Comprehension (arxiv.org) |
|
2 points by Jimmc414 on Sep 20, 2023 | hide | past | pdf | 1 comment
|
|
| 4. |
The Cognitive Strengths and Weaknesses of Modern LLMs (arxiv.org) |
|
2 points by vishnumenon on Sep 20, 2023 | hide | past | pdf | discuss
|
|
| 5. |
Neurosymbolic Meta-Reinforcement Learning Achieves Safe Self-Driving (arxiv.org) |
|
2 points by PaulHoule on Sep 20, 2023 | hide | past | pdf | discuss
|
|
| 6. |
Can Deep Neural Networks Predict Data Correlations from Column Names? (arxiv.org) |
|
2 points by PaulHoule on Sep 20, 2023 | hide | past | pdf | 1 comment
|
|
| 7. |
Fast Feedforward Networks (arxiv.org) |
|
2 points by jasondavies on Sep 20, 2023 | hide | past | pdf | 1 comment
|
|
| 8. |
Unsupervised Learning via Network-Aware Embeddings (arxiv.org) |
|
2 points by mikk14 on Sep 20, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Program generation is all you need? For math, symbolic, natural language, etc. (arxiv.org) |
|
1 point by hyluo on Sep 20, 2023 | hide | past | pdf | 1 comment
|
|
| 10. |
Nougat: Neural Optical Understanding for Academic Documents (arxiv.org) |
|
1 point by signa11 on Sep 20, 2023 | hide | past | pdf | discuss
|
|
|
|
