arXiv 2609.35748 · cs.CL · 2026-09-28
Improving Test-Time Scaling with Adaptive Looped Transformers
Yichen You, Tianyu Fu, Aosong Feng, Xingtai Lv, Xuefei Ning, Ning Ding, Yu Wang
Tsinghua-NICS-EFC
在最新榜 #84 本站收录于 2026-10-21
一句话要点
研究循环 Transformer 在测试时扩展中的表现，并提出自适应循环以在同等算力下胜过基线。
Studies looped transformers under test-time scaling and proposes adaptive looping to beat baselines at matched compute.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：推理
- LEV: Thinking Fast and Deep with Looped Decision Models ▲602
- Thinking Inertia: LLMs Keep Thinking When Told Not To ▲241
- Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence ▲224
- Questioning the Questions: Sustaining Self-Evolution in Reasoning Models ▲85
- Hybrid Reasoning Agents ▲38
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。