arXiv Computation and Language
Test-Time Training with Next-Token Prediction
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jul 13
Self-Guided Test-Time Training for Long-Context LLMs
arXiv:2607. 09415v1 Announce Type: cross Abstract: Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long inputs.
arXiv Machine Learning
Aug 4
Learning What to Remember: Test-Time Training via Context Distillation
arXiv:2608. 01672v1 Announce Type: cross Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later.
arXiv Computation and Language
5d ago
Reinforced Fast Weights via Next-Sequence Prediction
The paper "Reinforced Fast Weights via Next-Sequence Prediction" introduces ReFINE, a method that extends the next-token prediction objective to next-sequence prediction for fast weight architectures. ReFINE selects informative token positions, generates multi-token rollouts, assigns sequence-level rewards, and optimizes the model using Group Relative Policy Optimization. Experiments on LaCT-760M and DeltaNet-1.3B demonstrate that ReFINE consistently outperforms standard next-token prediction fine‑tuning across retrieval, long‑context question answering, and LongBench tasks.
arXiv Machine Learning
Aug 24
Rethinking Expressivity and Efficiency in Test-Time Training
arXiv:2608.21308v1 Announce Type: new Abstract: Test-Time Training (TTT) enables long-context processing via continuous weight updates during inference, but current methods struggle to balance the ex...
arXiv AI
Oct 2
Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
arXiv:2610.00888v1 Announce Type: cross Abstract: Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per fo...
arXiv AI
Jul 24
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training
arXiv:2603. 06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering catastrophic failure on exact-recall tasks.