Test-Time Training

Test-time training studies how models can learn from the inputs they encounter during deployment, rather than relying only on a fixed model or a longer prompt. Methods update fast weights or lightweight adapters, optimize compact memories, or adjust prompts using signals such as next-token prediction, reconstruction, pseudo-labels, and environment feedback. These approaches are being explored for long-context language tasks, distribution shifts in vision and healthcare, streaming video, robotics, and reasoning. A central challenge is getting useful adaptation without excessive latency or harmful drift, especially when supervision is noisy or generated by the model itself; reliable behavioral evaluation and safety checks remain important.