|
|
|
Stories from November 29, 2023 (UTC)
|
| 1. |
Scheming AIs Will AIs fake alignment during training in order to get power?[pdf] (arxiv.org) |
|
5 points by kelseyfrog on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 2. |
Scalable Extraction of Training Data from (Production) Language Models (arxiv.org) |
|
5 points by nabla9 on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 3. |
Extracting Training Data from LLMs (arxiv.org) |
|
4 points by niyikiza on Nov 29, 2023 | hide | past | pdf | 1 comment
|
|
| 4. |
Current Time Series Anomaly Detection Benchmarks Are Flawed (arxiv.org) |
|
2 points by bsoles on Nov 29, 2023 | hide | past | pdf | 5 comments
|
|
| 5. |
Aligning diffusion models to human preferences with DPO (arxiv.org) |
|
2 points by variational123 on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 6. |
Can Generalist Foundation Models Outcompete Special-Purpose Tuning? (Medical QA) (arxiv.org) |
|
2 points by vok on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 7. |
A Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers (arxiv.org) |
|
2 points by PaulHoule on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 8. |
Deep Neuromorphic Networks with Superconducting Single Flux Quanta (arxiv.org) |
|
2 points by PaulHoule on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 9. |
Few-Shot Classification and Segmentation Using Large Language Models Agent (arxiv.org) |
|
1 point by PaulHoule on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 10. |
MobileCLIP: Fast Image-Text Models Through Multi-Modal Reinforced Training (arxiv.org) |
|
1 point by zerojames on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 11. |
Meditron-70B: Scaling Medical Pretraining for Large Language Models (arxiv.org) |
|
1 point by tosh on Nov 29, 2023 | hide | past | pdf | discuss
|
|
| 12. |
Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction (arxiv.org) |
|
1 point by PaulHoule on Nov 29, 2023 | hide | past | pdf | discuss
|
|
|
|
