āļ„āļđāđˆāļĄāļ·āļ­āļžāļ·āđ‰āļ™āļāļēāļ™

āļāļēāļĢāļāļķāļāļ­āļšāļĢāļĄāđ€āļ§āļĨāļēāļ—āļ”āļŠāļ­āļš

Test-time training updates a model from an unlabeled input before making a prediction in the cited adaptation work.

āļŸāļąāļ‡āļ„āļģāđāļ™āļ°āļ™āļģāļ™āļĩāđ‰āļšāļĢāļĢāļĒāļēāļĒāđ‚āļ”āļĒ AI · ~3 min

āļšāļ™āļŦāļ™āđ‰āļēāļ™āļĩāđ‰āļ­āđˆāļēāļ™ 3 āļ™āļēāļ—āļĩ
  1. āļ āļēāļžāļĢāļ§āļĄ
  2. āđ€āļˆāļēāļ°āļĨāļķāļ
  3. āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļˆāļĢāļīāļ‡āđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡
  4. āļ­āļ™āļēāļ„āļ•āļ‚āļ­āļ‡āļāļēāļĢāļāļķāļāļ­āļšāļĢāļĄāļŠāđˆāļ§āļ‡āļ—āļ”āļŠāļ­āļš
  5. āļāļēāļĢāļ™āļģāđ„āļ›āļ›āļāļīāļšāļąāļ•āļī
  6. āļŠāļģāļĢāļ§āļˆāļ•āđˆāļ­āđ„āļ›
  7. āļ„āļģāļ–āļēāļĄāļ—āļĩāđˆāļžāļšāļšāđˆāļ­āļĒ

āļ āļēāļžāļĢāļ§āļĄ

TTT sequence layers use a related learning idea for recurrent state updates; these are distinct research setups with measured benefits and limitations.

āđ€āļˆāļēāļ°āļĨāļķāļ

A deployed classifier can encounter inputs that differ from its training distribution. Test-Time Training with Self-Supervision for Generalization under Distribution Shifts studies adapting model parameters on an unlabeled test sample before predicting its main label. It uses a self-supervised task whose target can be constructed without knowing that label, such as recognizing a rotation applied to an image. This is different from using the unknown correct class as training data. The reported classification improvements apply to the tested distribution shifts and setup rather than every possible deployment. Learning to Learn at Test Time develops another use of this idea for sequence modeling. A TTT layer’s hidden state is the parameter set of an inner model, updated through a self-supervised learning rule along the sequence. The paper studies a linear inner model, TTT-Linear, and a two-layer multilayer perceptron, TTT-MLP. This fixed-size recurrent state provides linear sequence-length complexity under the stated fixed model dimensions and update procedure, whereas ordinary dense attention has a quadratic pairwise term. Linear complexity does not guarantee lower latency on every device, because implementation and memory access also matter. The outer training loop optimizes the surrounding network and learned components of the inner self-supervised task for the language-model objective. The inner loop instead updates the state model’s weights on the current sequence. A sequence-state update should not be described as necessarily rewriting every deployed language-model weight or retaining personal information across every future request.

āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļˆāļĢāļīāļ‡āđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡

Studying image-classifier adaptation on a defined corruption benchmark.

Computing a self-supervised auxiliary loss from an incoming unlabeled image.

Comparing TTT-Linear and TTT-MLP recurrent hidden-state models.

Inspecting which parameters belong to a sequence layer’s inner and outer learning loops.

āļ­āļ™āļēāļ„āļ•āļ‚āļ­āļ‡āļāļēāļĢāļāļķāļāļ­āļšāļĢāļĄāļŠāđˆāļ§āļ‡āļ—āļ”āļŠāļ­āļš

Test-time learning experiments can compare adaptation objectives, update budgets, and input distributions while checking whether main-task accuracy improves. Sequence models can also compare inner-state architectures and implementation costs over stated context lengths. Reliability evaluation should include cases where an auxiliary improvement fails to improve the intended prediction. A proposed deployment needs a clear account of which state changes, when it is reset, and how behavior is measured. Those questions are more useful than assuming that learning during inference automatically gives better robustness or replaces every attention-based model.

āļāļēāļĢāļ™āļģāđ„āļ›āļ›āļāļīāļšāļąāļ•āļī

āļ—āļģāđ„āļĄāļĄāļąāļ™āļ–āļķāļ‡āļŠāļģāļ„āļąāļ

  • āļāļēāļĢāļ•āļąāļ”āļŠāļīāļ™āđƒāļˆāļ—āļĩāđˆāļŠāļąāļ”āđ€āļˆāļ™āļĒāļīāđˆāļ‡āļ‚āļķāđ‰āļ™. āļŠāđˆāļ§āļĒāđƒāļŦāđ‰āļ„āļļāļ“āđāļĒāļāļ„āļģāļāļĨāđˆāļēāļ§āļ­āđ‰āļēāļ‡āļ—āļēāļ‡āđ€āļ—āļ„āļ™āļīāļ„āļ—āļĩāđˆāļŠāļąāļ”āđ€āļˆāļ™āļ­āļ­āļāļˆāļēāļāļ āļēāļĐāļēāļ—āļēāļ‡āļāļēāļĢāļ•āļĨāļēāļ”āđ„āļ”āđ‰
  • āļ•āđ‰āļ™āļ—āļļāļ™āđāļĨāļ°āļ‡āļšāļ›āļĢāļ°āļĄāļēāļ“. āļ„āļļāļ“āļŠāļēāļĄāļēāļĢāļ–āļ–āļēāļĄāļ„āļģāļ–āļēāļĄāļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļ—āļĩāđˆāļ”āļĩāļ‚āļķāđ‰āļ™āļāđˆāļ­āļ™āļ—āļĩāđˆāļˆāļ°āđƒāļŠāđ‰āđ€āļ‡āļīāļ™āļŦāļĢāļ·āļ­āđ€āļ§āļĨāļē
  • āļ—āļĩāļĄāļ‡āļēāļ™āđāļĨāļ°āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āļāļēāļĢāļ—āļģāļ‡āļēāļ™. āļ—āļĩāļĄāļ—āļĩāđˆāļĄāļĩāļ„āļ§āļēāļĄāđ€āļ‚āđ‰āļēāđƒāļˆāļĢāđˆāļ§āļĄāļāļąāļ™āļˆāļ°āļ•āļąāļ”āļŠāļīāļ™āđƒāļˆāđ€āļāļĩāđˆāļĒāļ§āļāļąāļšāļœāļĨāļīāļ•āļ āļąāļ“āļ‘āđŒ āļ™āđ‚āļĒāļšāļēāļĒ āđāļĨāļ°āļāļēāļĢāđ€āļĢāļĩāļĒāļ™āļĢāļđāđ‰āđ„āļ”āđ‰āļ”āļĩāļ‚āļķāđ‰āļ™

āļĢāļ°āļ§āļąāļ‡

  • āđāļ•āđˆāļĨāļ°āļ—āļĩāļĄāļ­āļēāļˆāđƒāļŠāđ‰āļ„āļģāđ€āļ”āļĩāļĒāļ§āļāļąāļ™āļ•āđˆāļēāļ‡āļāļąāļ™ āļ”āļąāļ‡āļ™āļąāđ‰āļ™āļ„āļ§āļĢāļāļģāļŦāļ™āļ”āļ‚āļ­āļšāđ€āļ‚āļ•āļ•āļąāđ‰āļ‡āđāļ•āđˆāđ€āļ™āļīāđˆāļ™āđ†
  • āđ€āļāļ“āļ‘āđŒāļĄāļēāļ•āļĢāļāļēāļ™āļ­āļēāļˆāļ”āļđāđāļ‚āđ‡āļ‡āđāļāļĢāđˆāļ‡āđƒāļ™āļ‚āļ“āļ°āļ—āļĩāđˆāļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļžāđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡āđ„āļĄāđˆāđ€āļ—āđˆāļēāļāļąāļ™
  • āļāļēāļĢāđ€āļžāļīāļāđ€āļ‰āļĒāļ•āđˆāļ­āļ„āļļāļ“āļ āļēāļžāļ‚āđ‰āļ­āļĄāļđāļĨāđāļĨāļ°āđāļœāļ™āļāļēāļĢāļ›āļĢāļ°āđ€āļĄāļīāļ™āļĄāļąāļāļŠāļĢāđ‰āļēāļ‡āļœāļĨāļĨāļąāļžāļ˜āđŒāļ—āļĩāđˆāđ€āļ›āļĢāļēāļ°āļšāļēāļ‡

āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āļ•āđˆāļ­āđ„āļ›

  1. āđ€āļĢāļīāđˆāļĄāļ•āđ‰āļ™āļ”āđ‰āļ§āļĒāļ„āļģāļˆāļģāļāļąāļ”āļ„āļ§āļēāļĄāļ āļēāļĐāļēāļ˜āļĢāļĢāļĄāļ”āļēāļ‚āļ­āļ‡āļœāļĨāļĨāļąāļžāļ˜āđŒāļ—āļĩāđˆāļ„āļļāļ“āļ•āđ‰āļ­āļ‡āļāļēāļĢ
  2. āđ€āļĨāļ·āļ­āļāđ€āļĄāļ•āļĢāļīāļāļ§āļąāļ”āļ„āļ§āļēāļĄāļŠāļģāđ€āļĢāđ‡āļˆāļŦāļ™āļķāđˆāļ‡āļĢāļēāļĒāļāļēāļĢāđāļĨāļ°āđ€āļ‡āļ·āđˆāļ­āļ™āđ„āļ‚āļ„āļ§āļēāļĄāļĨāđ‰āļĄāđ€āļŦāļĨāļ§āļŦāļ™āļķāđˆāļ‡āļĢāļēāļĒāļāļēāļĢāļāđˆāļ­āļ™āļāļēāļĢāļ—āļ”āļŠāļ­āļš
  3. āļ”āļģāđ€āļ™āļīāļ™āļāļēāļĢāļ™āļģāļĢāđˆāļ­āļ‡āļ‚āļ™āļēāļ”āđ€āļĨāđ‡āļāļ”āđ‰āļ§āļĒāļ‚āđ‰āļ­āļĄāļđāļĨāļ•āļąāļ§āđāļ—āļ™ āđ„āļĄāđˆāđƒāļŠāđˆāļŠāļļāļ”āļŠāļēāļ˜āļīāļ•āļ—āļĩāđˆāļŠāļ§āļĒāļ‡āļēāļĄ
  4. āđ€āļ­āļāļŠāļēāļĢāļ—āļĩāđˆāļāļēāļĢāļāļķāļāļ­āļšāļĢāļĄāđ€āļ§āļĨāļēāļ—āļ”āļŠāļ­āļšāļŠāđˆāļ§āļĒāđ„āļ”āđ‰ āđāļĨāļ°āļ§āļīāļ˜āļĩāļ—āļĩāđˆāļ‡āđˆāļēāļĒāļāļ§āđˆāļēāļˆāļ°āļ”āļĩāļāļ§āđˆāļē

āļŠāļģāļĢāļ§āļˆāļ•āđˆāļ­āđ„āļ›

āļˆāļ”āļŦāļĄāļēāļĒāļ‚āđˆāļēāļ§āļŸāļĢāļĩ

āļĢāļąāļšāļŠāļĢāļļāļ› AI āļĢāļēāļĒāļ§āļąāļ™

āđ€āļĢāļ·āđˆāļ­āļ‡āļĢāļēāļ§ AI āļ—āļĩāđˆāļ•āļĢāļ§āļˆāļŠāļ­āļšāđāļĨāđ‰āļ§ 3 āđ€āļĢāļ·āđˆāļ­āļ‡āļ—āļļāļāļ§āļąāļ™āļ—āļģāļ‡āļēāļ™ āđ€āļŠāđ‰āļē, āđ€āļ‚āļĩāļĒāļ™āđ€āļ›āđ‡āļ™āļ āļēāļĐāļēāļ­āļąāļ‡āļāļĪāļĐāļ˜āļĢāļĢāļĄāļ”āļē āļŸāļĢāļĩāļ•āļĨāļ­āļ”āđ„āļ› āđ„āļĄāđˆāļĄāļĩāđ‚āļ†āļĐāļ“āļē

āļ­āļĩāđ€āļĄāļĨāļŦāļ™āļķāđˆāļ‡āļ‰āļšāļąāļšāļ—āļļāļāļ§āļąāļ™āļ—āļģāļ‡āļēāļ™ āļĒāļāđ€āļĨāļīāļāļāļēāļĢāļŠāļĄāļąāļ„āļĢāđƒāļ™āļ„āļĨāļīāļāđ€āļ”āļĩāļĒāļ§ āđ€āļĢāļēāđ„āļĄāđˆāđ€āļ„āļĒāļ‚āļēāļĒāļŦāļĢāļ·āļ­āđāļŠāļĢāđŒāļ—āļĩāđˆāļ­āļĒāļđāđˆāļ­āļĩāđ€āļĄāļĨāļ‚āļ­āļ‡āļ„āļļāļ“

āļ—āļ”āļŠāļ­āļšāļ•āļąāļ§āđ€āļ­āļ‡

Take the Test-Time Training quiz

āļ‚āđ‰āļ­āđ€āļŠāļ™āļ­āđāļ™āļ°āļ—āļąāļ™āļ—āļĩāļŠāļģāļŦāļĢāļąāļšāļ—āļļāļāļ„āļģāļ•āļ­āļš āđāļĨāļ°āđƒāļšāļĢāļąāļšāļĢāļ­āļ‡āļ—āļĩāđˆāļŠāļēāļĄāļēāļĢāļ–āđāļŠāļĢāđŒāđ„āļ”āđ‰āļžāļĢāđ‰āļ­āļĄ ID āļ—āļĩāđˆāļ•āļĢāļ§āļˆāļŠāļ­āļšāđ„āļ”āđ‰āđ€āļĄāļ·āđˆāļ­āļ„āļļāļ“āļœāđˆāļēāļ™āļŦāļĨāļąāļāļŠāļđāļ•āļĢ

āđ€āļĢāļīāđˆāļĄāđāļšāļšāļ—āļ”āļŠāļ­āļš

āļŠāļ™āļąāļšāļŠāļ™āļļāļ™āļāļēāļĢāļĻāļķāļāļĐāļē AI āļŸāļĢāļĩ AI Understanding āđ€āļ›āđ‡āļ™āļ­āļ‡āļ„āđŒāļāļĢāđ„āļĄāđˆāđāļŠāļ§āļ‡āļŦāļēāļœāļĨāļāļģāđ„āļĢ 501(c)(3) — āđ„āļĄāđˆāļĄāļĩāđ‚āļ†āļĐāļ“āļē āđ„āļĄāđˆāļĄāļĩāļāļģāđāļžāļ‡āđ€āļ‡āļīāļ™, āļ•āļĨāļ­āļ”āđ„āļ› āļšāļĢāļīāļˆāļēāļ„

āļ„āļģāļ–āļēāļĄāļ—āļĩāđˆāļžāļšāļšāđˆāļ­āļĒ

What is Test-Time Training?

Test-time training updates a model from an unlabeled input before making a prediction in the cited adaptation work. TTT sequence layers use a related learning idea for recurrent state updates; these are distinct research setups with measured benefits and limitations.

What happens in the cited classic test-time training adaptation procedure before the main prediction?

The update uses a computable self-supervised problem derived from the input.

āđ€āļŦāļ•āļļāđƒāļ” TTT āđāļšāļšāļ„āļĨāļēāļŠāļŠāļīāļāļˆāļķāļ‡āļ•āđ‰āļ­āļ‡āļžāļķāđˆāļ‡āļžāļēāļ‡āļēāļ™āđ€āļŠāļĢāļīāļĄāļ—āļĩāđˆāļĄāļĩāļāļēāļĢāļ”āļđāđāļĨāļ•āļ™āđ€āļ­āļ‡

āđ€āļ™āļ·āđˆāļ­āļ‡āļˆāļēāļāđ„āļĄāđˆāļ—āļĢāļēāļšāļ›āđ‰āļēāļĒāļāļģāļāļąāļšāļ—āļĩāđˆāđāļ—āđ‰āļˆāļĢāļīāļ‡āļ‚āļ­āļ‡āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āļāļēāļĢāļ—āļ”āļŠāļ­āļš TTT āļˆāļķāļ‡āđƒāļŠāđ‰āļ‡āļēāļ™āđ€āļŠāđˆāļ™āļāļēāļĢāļ—āļģāļ™āļēāļĒāļāļēāļĢāļŦāļĄāļļāļ™āļŦāļĢāļ·āļ­āļāļēāļĢāļŠāļĢāđ‰āļēāļ‡āđƒāļŦāļĄāđˆāđāļšāļšāļŠāļ§āļĄāļŦāļ™āđ‰āļēāļāļēāļāļ‹āļķāđˆāļ‡āļāļēāļĢāļŠāļđāļāđ€āļŠāļĩāļĒāđ„āļĄāđˆāļˆāļģāđ€āļ›āđ‡āļ™āļ•āđ‰āļ­āļ‡āļĄāļĩāļ›āđ‰āļēāļĒāļāļģāļāļąāļš

What forms the recurrent hidden state of a TTT sequence layer?

The inner model’s changing parameters encode sequence information.

Under fixed inner-model dimensions and update work, how does TTT sequence-layer complexity scale with sequence length?

The paper’s linear complexity is an architectural scaling result, not a universal wall-clock guarantee.

What problem motivated the cited classic test-time adaptation study?

The study evaluates adaptation under distribution shifts in image-classification benchmarks.

āđ€āļĢāļĩāļĒāļ™āļĢāļđāđ‰āļ•āđˆāļ­āđ„āļ›

āļ„āļģāđāļ™āļ°āļ™āļģāļ—āļĩāđˆāđ€āļāļĩāđˆāļĒāļ§āļ‚āđ‰āļ­āļ‡

āļ„āļģāđāļ™āļ°āļ™āļģāđ€āļžāļīāđˆāļĄāđ€āļ•āļīāļĄāļ—āļĩāđˆāđ€āļĨāļ·āļ­āļāļŠāļģāļŦāļĢāļąāļšāļŦāļąāļ§āļ‚āđ‰āļ­āļ™āļĩāđ‰

āļ•āđˆāļ­āđ„āļ›āļ„āļģāđāļ™āļ°āļ™āļģāļ•āđˆāļ­āđ„āļ›

āļāļēāļĢāđ€āļžāļīāđˆāļĄāđ€āļ§āļĨāļēāļ—āļ”āļŠāļ­āļš

āđ€āļ—āļ„āļ™āļīāļ„

āļĢāļąāļšāđƒāļšāļĢāļąāļšāļĢāļ­āļ‡ AI āļŸāļĢāļĩāļŦāļĨāļąāļāļŠāļđāļ•āļĢāđāļĨāļ°āļāļēāļĢāļŠāļ­āļšāļŠāļąāđ‰āļ™ āđ† āļŸāļĢāļĩ āđ„āļĄāđˆāļĄāļĩāļ„āđˆāļēāđƒāļŠāđ‰āļˆāđˆāļēāļĒ āđ„āļĄāđˆāļĄāļĩāļšāļąāļ•āļĢāđ€āļ„āļĢāļ”āļīāļ• āļ›āļĢāļ°āļĄāļēāļ“ 2.5 āļŠāļąāđˆāļ§āđ‚āļĄāļ‡āđ€āļĢāļīāđˆāļĄāļ•āđ‰āļ™āļŸāļĢāļĩ →