PonderTTT – Training-free adaptive compute for LLMs via TTT gating

Show HN: PonderTTT – Training-free adaptive compute for LLMs via TTT gating

PonderTTT – Training-free adaptive compute for LLMs via TTT gating is a company in show hn launch.

Profile

Hi HN,This is my first project/paper (independent work; I’m a high school student in Korea).PonderTTT explores when to run Test-Time Training (TTT) updates instead of updating on every segment.The gate is training-free: it uses the TTT layer's self-supervised reconstruction loss to decide UPDATE vs SKIP.A single threshold is calibrated on unlabeled data and adapted online via EMA to maintain a target update rate.In GPT-2 code language modeling experiments (124M–1.5B), this reached 82–89% Oracle Recovery and improved over Random Skip baselines on some OOD languages (up to 16% lower loss).Note: v1 experiments are JAX/Flax on GPUs. I'm working on a v2 scale-up to Gemma 3 (TPU).I'd really apprec

PonderTTT – Training-free adaptive compute for LLMs via TTT gating is positioned in show hn launch, a segment that rewards a clear, focused offering.

The company is listed at the Show HN launch stage of development.

Website: ponderttt.worldsw.dev