|
|
|
Stories from September 25, 2025 (UTC)
|
| 1. |
The Illusion of Readiness: Stress Testing Frontier Models on Medical Benchmarks (arxiv.org) |
|
6 points by mellosouls on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 2. |
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2 (arxiv.org) |
|
3 points by matt_d on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 3. |
TimeCopilot: Framework for Forecasting combining Time Series Models with LLMs (arxiv.org) |
|
2 points by favoboa on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 4. |
SimpleFold: Folding Proteins Is Simpler Than You Think (arxiv.org) |
|
2 points by gok on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 5. |
Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe (arxiv.org) |
|
1 point by JnBrymn on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 6. |
Just-in-time and distributed task representations in language models (arxiv.org) |
|
1 point by PaulHoule on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 7. |
Quantized LLMss in Biomedical Natural Language Processing (arxiv.org) |
|
1 point by PaulHoule on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 8. |
Ransomware 3.0: Self-Composing and LLM-Orchestrated (arxiv.org) |
|
1 point by PaulHoule on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 9. |
Multi-Modal vs. Text-Based: Benchmarking LLM Strategies for Invoice Processing (arxiv.org) |
|
1 point by PaulHoule on Sep 25, 2025 | hide | past | pdf | discuss
|
|
| 10. |
LIMI: Less Is More for Agency (arxiv.org) |
|
1 point by pella on Sep 25, 2025 | hide | past | pdf | discuss
|
|
|
|
