Test-Time Training

Also known as TTT

Overview

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.

Latest papers

CardsList

111 papers10 papers in the last four weeks, down 64% on the four weeks before. 0.1% of all new papers.

  1. TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models

    Nov 12, 2026Chin-Yang Lin, Ryo Hachiuma, Jaesung Choe +6Novel View SynthesisNeural Rendering

  2. How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

    Nov 9, 2026Ku Onoda, Haruto Kawano, Shota Takashiro +1Game World ModelsWorld Model Learning

  3. Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training

    Nov 3, 2026Vimal William, Yuanzhe Li, Danella Zhao +1Memory-Augmented Language ModelsLong-Context Retrieval

  4. Spectral-spatial vision test-time training for hyperspectral image classification

    Nov 2, 2026Xiang ZhaoHyperspectral Image ClassificationHyperspectral Imaging

  5. ParaTTT: Parallelizing Test-Time Training Layers with Deep Memories

    Oct 28, 2026Noel Loo, Neehal Tumma, T. Konstantin Rusch +3Test-Time TrainingRecurrent Language Models

  6. Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training

    Oct 27, 2026Yue Wu, Yang Zhang, Weinan Gan +4Test-Time TrainingInference-Time Adaptation of Language Models

  7. Diagnosing the Explicit-to-Applied Theory of Mind Gap in LLMs

    Oct 22, 2026Prajvi Saxena, Sabine Janzen, Wolfgang MaassTheory of MindLanguage Model Reasoning Evaluation

  8. Memory Internalization via Test-Time Training for Long-Video Understanding

    Oct 17, 2026Haonan Zhao, Jiaxuan Chen, Qingyang Liu +4Memory-Augmented Video UnderstandingLong-Video QA

  9. Latent Compaction with Test-Time Training

    Oct 14, 2026Yingfa Chen, Xingyu Shen, Chaojun Xiao +1LLM Context CompressionKV-Cache Compression

  10. MMLA-RSI: Recursive Self-Improvement through RTT and RTMA

    Oct 14, 2026Junyi Zou, Avrova DonzSelf-Improving AgentsRecursive Self-Improvement

  11. Encoding Context into LLM Weights: What Makes It Context?

    Oct 13, 2026Yue Wang, Qizhou Wang, Feng Liu +3LLM Context ManagementTest-Time Training

  12. World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models

    Oct 12, 2026Junyi Wu, Zekun Li, Chenhongyi Yang +9Video World ModelsMemory-Augmented Video Generation

  13. HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery

    Oct 12, 2026Yingzi Ma, Yulong Cao, Nanxi Li +5Agent Harness OptimizationLLM Agent Harnesses

  14. ChangeT3^3: Evaluating Vision Test-Time Training for Remote Sensing Change Detection

    Oct 11, 2026Sharukshan Niranjan, Oshadha Samarakoon, Nichula Wasalathilaka +3Remote Sensing Change DetectionTest-Time Training

  15. Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM

    Oct 9, 2026Adrien Deliege, Marc Van DroogenbroeckRecursive Reasoning ModelsAbstract Reasoning

  16. Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory

    Oct 9, 2026Vakul Raghavan, Utkarsh Grover, Mingyang Mao +2Long-Context ModelingMemory-Augmented Neural Networks

  17. Agentic-TTT: Training test-time policy for test-time training

    Oct 8, 2026Jiahao Lu, Mohan KankanhalliTest-Time TrainingLLM Agent Self-Improvement

  18. DeltaTTT: Layerwise Optimization for Nonlinear Recurrent Memory

    Oct 6, 2026Yining Li, Dongchen Han, Jie Fu +1Deep Learning OptimizationNeural Network Optimization

  19. Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries

    Oct 5, 2026Chonghe Jiang, Ao Qu, Siyuan Liu +9Large Language Model-Guided OptimizationTest-Time RL

  20. Universal Test-Time Training

    Oct 4, 2026Zefan Cai, Qinzhe Hu, Ziqiao Ma +2Memory-Augmented Language ModelsRecurrent Transformers

  21. Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models

    Oct 4, 2026Tongyan Hu, Hao Li, Xiaogeng Liu +8Test-Time TrainingLLM Jailbreak Attacks

  22. Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation

    Oct 4, 2026Cheng Luo, Bing Li, Bernard GhanemTest-Time AdaptationContinual Test-Time Adaptation