|
|
|
Stories from April 25, 2024 (UTC)
|
| 1. |
Quaternion Knowledge Graph Embeddings (2019) (arxiv.org) |
|
100 points by teleforce on Apr 25, 2024 | hide | past | pdf | 41 comments
|
|
| 2. |
CatLIP: Clip Vision Accuracy with 2.7x Faster Pre-Training on Web-Scale Data (arxiv.org) |
|
48 points by panabee on Apr 25, 2024 | hide | past | pdf | 4 comments
|
|
| 3. |
A high-bias, low-variance introduction to Machine Learning for physicists (arxiv.org) |
|
5 points by teleforce on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 4. |
NExT: Teaching Large Language Models to Reason about Code Execution (arxiv.org) |
|
4 points by tosh on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 5. |
Scaling Laws vs. Model Architectures: How Does Inductive Bias Influence Scaling? (arxiv.org) |
|
3 points by georgehill on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 6. |
Manipulating Large Language Models to Increase Product Visibility (arxiv.org) |
|
2 points by fauigerzigerk on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 7. |
COCONut: Modernizing Coco Segmentation (arxiv.org) |
|
2 points by petargyurov on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 8. |
Retrieval Head Mechanistically Explains Long-Context Factuality (arxiv.org) |
|
2 points by tosh on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 9. |
FPGA Divide-and-Conquer Placement Using Deep Reinforcement Learning (arxiv.org) |
|
2 points by PaulHoule on Apr 25, 2024 | hide | past | pdf | discuss
|
|
| 10. |
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions (arxiv.org) |
|
1 point by tosh on Apr 25, 2024 | hide | past | pdf | discuss
|
|
|
|
