arXiv 2610.06833 · cs.LG · 2026-10-05
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
Benhao Huang, Chufan Shi, Junlin Chen, Shicheng Wen, Zhengzhong Liu, Eric Xing, Xuezhe Ma
Institute of Foundation Models
In latest · #201 Added on 2026-10-21
One-line takeaway
Driving looped language models towards fixed points enables truncated backprop, KV sharing and cheaper RL with little accuracy loss.
循环语言模型的状态越接近不动点，训练、解码和强化学习都能走捷径，从而大幅省算力。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Efficient training & inference
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲251
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.