PredictLM v11.0 + Mini ship-bundle
Browse files
README.md
CHANGED
|
@@ -86,6 +86,8 @@ That's it. On the first `.predict()` call the package silently downloads its par
|
|
| 86 |
|
| 87 |
**TTT** ([Test-Time Training](https://arxiv.org/abs/2503.11842), grounded in TabPFN-2.5's [recipe](https://arxiv.org/abs/2511.08667)) does ~15 inner Adam steps of self-supervised fine-tuning on the user's in-context examples before predicting. Per-task specialization on top of a generic ICL prior. 19 / 20 datasets improved vs zero-tuning; no dataset regressed by more than 0.006.
|
| 88 |
|
|
|
|
|
|
|
| 89 |
## Developers and affiliations
|
| 90 |
|
| 91 |
- **Developed by**: ZeroOne Research
|
|
|
|
| 86 |
|
| 87 |
**TTT** ([Test-Time Training](https://arxiv.org/abs/2503.11842), grounded in TabPFN-2.5's [recipe](https://arxiv.org/abs/2511.08667)) does ~15 inner Adam steps of self-supervised fine-tuning on the user's in-context examples before predicting. Per-task specialization on top of a generic ICL prior. 19 / 20 datasets improved vs zero-tuning; no dataset regressed by more than 0.006.
|
| 88 |
|
| 89 |
+
PredictLM's TTT is an independent implementation of the published technique. This repo does not include or derive from TabPFN code or weights — PredictLM weights are trained from scratch (Mini distilled from PredictLM-Base) and shipped under Apache-2.0.
|
| 90 |
+
|
| 91 |
## Developers and affiliations
|
| 92 |
|
| 93 |
- **Developed by**: ZeroOne Research
|