Self-Guided Test-Time Training for Long-Context LLMs
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. As input length grows, accuracy often degrades, indicating that models still struggle to identify and use the evidence most relevant to a question. A promising way to improve long-context utilization is test-time training (TTT), which treats the test context as a training example for instance-specific parameter adaptation. However, applying TTT to the entire long context is prohibitively expensive, while ada
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%RimantasZ/contextspy →
- PossiblePossibly related (embedding) · 53%Breakthrough in long-context efficiency announced →
- PossiblePossibly related (embedding) · 52%thu-pacman/chitu →
- PossiblePossibly related (embedding) · 49%chrisliu298/awesome-llm-unlearning →
- PossiblePossibly related (embedding) · 48%Context window →
- LinkedLinked via arxiv author · 85%Xinyu Zhu →
“Self-Guided Test-Time Training for Long-Context LLMs”
- LinkedLinked via arxiv author · 85%Zhe Xu →
“Self-Guided Test-Time Training for Long-Context LLMs”
- LinkedLinked via arxiv author · 85%Xiaohan Wei →
“Self-Guided Test-Time Training for Long-Context LLMs”