arXiv (All)
open access
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation
Test-time training (TTT) lets a model store information in its weights during inference. When the model learns from its own output, however, each update also changes the model that generates the next training example. Across 128K-token streams, retaining generated-text updates worsens prediction on
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- DriftAudio: Marginal Drifting for Distributional Post-Training of One-Step Text-to-Audio Generators#1064142
- Improving Generative Model Self-Training with Geometrically Modified Outputs#1130093
- Training on the Future: A Delay-Aware Audit of Test-Time Adaptation for Time-Series Forecasting#1249656
- Training on the Future: A Delay-Aware Audit of Test-Time Adaptation for Time-Series Forecasting#1242762
- Correction-space Cross-variate Interaction for Test-time Adaptation in Time Series Forecasting#1128900
Record · ID 1201089
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive