Back to home

Tag

test-time training

Test-time training refers to models that keep adapting during inference with small updates from the current input. It shows up in long-context LLMs, 4D reconstruction, and continual perception, where it helps reduce forgetting and improve online adaptation.

2 articles

Fast Spatial Memory for Long 4D Sequences
Research/Apr 9

Fast Spatial Memory for Long 4D Sequences

A new 4D reconstruction model uses elastic test-time training to reduce forgetting and memory bottlenecks in long-sequence spatial learning.

In-Place TTT Lets LLMs Adapt at Inference
Research/Apr 8

In-Place TTT Lets LLMs Adapt at Inference

A new test-time training setup lets LLMs update fast weights in place, aiming for better long-context adaptation without full retraining.