| 1. |
A Cookbook of Self-Supervised Learning (arxiv.org) |
|
178 points by ZunarJ5 on Apr 25, 2023 | hide | past | pdf | 22 comments
|
|
| 2. |
Tighter bounds on the expressivity of transformer encoders (arxiv.org) |
|
76 points by bmc7505 on Apr 25, 2023 | hide | past | pdf | 13 comments
|
|
| 3. |
On-Device Acceleration of Large Diffusion Models (arxiv.org) |
|
9 points by mztwo on Apr 25, 2023 | hide | past | pdf | 3 comments
|
|
| 4. |
A Cookbook of Self-Supervised Learning (arxiv.org) |
|
5 points by nothrowaways on Apr 25, 2023 | hide | past | pdf | 1 comment
|
|
| 5. |
Can ChatGPT be used to generate scientific hypotheses? (arxiv.org) |
|
4 points by belter on Apr 25, 2023 | hide | past | pdf | 1 comment
|
|
| 6. |
Language Models Are Realistic Tabular Data Generators (arxiv.org) |
|
3 points by PaulHoule on Apr 25, 2023 | hide | past | pdf | 1 comment
|
|
| 7. |
Can GPT-4 Perform Neural Architecture Search? (arxiv.org) |
|
3 points by gat1 on Apr 25, 2023 | hide | past | pdf | discuss
|
|
| 8. |
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets (arxiv.org) |
|
3 points by thenobsta on Apr 25, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Fundamental Limitations of Alignment in Large Language Models (arxiv.org) |
|
3 points by 0xBABAD00C on Apr 25, 2023 | hide | past | pdf | discuss
|
|
| 10. |
Emergent and Predictable Memorization in Large Language Models (arxiv.org) |
|
3 points by ftxbro on Apr 25, 2023 | hide | past | pdf | discuss
|
|
| 11. |
Evaluating ChatGPT's Information Extraction Capabilities: An Assessment (arxiv.org) |
|
2 points by yarapavan on Apr 25, 2023 | hide | past | pdf | 1 comment
|
|
| 12. |
GPT4 can surpass humans in Theory of Mind test, with appropriate prompt (arxiv.org) |
|
2 points by rodoxcasta on Apr 25, 2023 | hide | past | pdf | 1 comment
|
|
| 13. |
SurgicalGPT: GPT for Visual Question Answering in Surgery (arxiv.org) |
|
2 points by rodoxcasta on Apr 25, 2023 | hide | past | pdf | discuss
|
|
