|
|
|
Stories from January 6, 2025 (UTC)
|
| 1. |
Time-Series Anomaly Detection: A Decade Review (arxiv.org) |
|
446 points by belter on Jan 6, 2025 | hide | past | pdf | 80 comments
|
|
| 2. |
Memory Layers at Scale (arxiv.org) |
|
4 points by PaulHoule on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 3. |
Study of AIAgents-driven Company: at best 24% of the tasks could be completed (arxiv.org) |
|
4 points by mentalgear on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 4. |
Frontier Models are Capable of In-context Scheming (arxiv.org) |
|
4 points by jimmcslim on Jan 6, 2025 | hide | past | pdf | 1 comment
|
|
| 5. |
Long Context vs. RAG for LLMs: An Evaluation and Revisits (arxiv.org) |
|
3 points by Jimmc414 on Jan 6, 2025 | hide | past | pdf | 4 comments
|
|
| 6. |
Superhuman performance of an LLM on the reasoning tasks of a physician (arxiv.org) |
|
2 points by Jimmc414 on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 7. |
Topology Meets ML: An Introduction Using the Euler Characteristic Transform (arxiv.org) |
|
2 points by Pseudomanifold on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 8. |
ICLR: In-Context Learning of Representations (arxiv.org) |
|
2 points by pama on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 9. |
Benchmarking LLM Agents on Consequential Real World Tasks (arxiv.org) |
|
2 points by iamflimflam1 on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 10. |
Don't Do RAG: When Cache-Augmented Generation Is All You Need for Knowledge Task (arxiv.org) |
|
1 point by ksec on Jan 6, 2025 | hide | past | pdf | discuss
|
|
| 11. |
An analytic theory of creativity in convolutional diffusion models (arxiv.org) |
|
1 point by RobinHirst11 on Jan 6, 2025 | hide | past | pdf | discuss
|
|
|
|
