| | GSM8K-Platinum: Revealing Performance Gaps in Frontier LLMs (gradientscience.org) |
| 2 points by todsacerdoti on March 7, 2025 | past |
|
| | Are there certain types of failures that pre-training alone cannot help with? (gradientscience.org) |
| 2 points by eitanturok on March 4, 2024 | past |
|
| | Show HN: Model-Aware Dataset Selection with Datamodels (DsDm) (gradientscience.org) |
| 2 points by logane on Jan 24, 2024 | past |
|
| | PhotoGuard: Defending Against Diffusion-Based Image Manipulation (gradientscience.org) |
| 2 points by chha on Dec 10, 2022 | past | 1 comment |
|
| | PhotoGuard: Defending Against Diffusion-Based Image Manipulation (gradientscience.org) |
| 3 points by polygamous_bat on Nov 4, 2022 | past |
|
| | Predicting Predictions with Datamodels (gradientscience.org) |
| 2 points by sebg on Feb 3, 2022 | past |
|
| | Debuggable Deep Networks: Sparse Linear Models (gradientscience.org) |
| 6 points by lnyan on May 12, 2021 | past |
|
| | Identifying Statistical Bias in Dataset Replication (gradientscience.org) |
| 1 point by logane on May 26, 2020 | past |
|
| | Adversarial Examples Are Not Bugs, They Are Features (gradientscience.org) |
| 2 points by erex78 on Aug 28, 2019 | past |
|
| | Adversarial Examples Are Not Bugs, They Are Features (gradientscience.org) |
| 1 point by erex78 on Aug 27, 2019 | past |
|
| | Representations by robust networks align much more closely with human perception (gradientscience.org) |
| 1 point by stared on June 6, 2019 | past |
|
| | How Does Batch Normalization Help Optimization? (gradientscience.org) |
| 3 points by diego898 on March 26, 2019 | past |
|
