Looped Transformer Scaling Research
BlackHC · x · 2026-07-18
Introduces DeepLoop: Depth Scaling for Looped Transformers.
Key message: Rumors suggest some frontier models essentially act like '48-layer Transformer looped twice' (48L × 2). This work proposes using looped transformer as a research object and focuses on solving its stability and scalability issues.
The emphasis is on advancing looped stacking of Transformers as a trainable and scalable architecture, not merely repeating rumors about model structure.
Related event: DeepLoop Explores Depth Scaling for Looped Transformers(2 posts)→
More from Research
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- Ben Recht: The world needs a truly open language model, and it's easier to build than you think — beenwrekt · 2026-10-26
- New Blog Breaks Black-Box Distillation Into Five Practical Steps — chrisrohlf · 2026-10-26
- DetectorScope turns black-box AI text detectors into auditable ones with sparse autoencoders — _akhaliq · 2026-10-26
- OPST paper shows LLMs self-improve with zero human data, guided only by topic descriptions — _akhaliq · 2026-10-26
- Tencent's HiSTEVE 1.0: hierarchical VLA agent plays Minecraft with native keyboard and mouse, hits 85% SOTA — _akhaliq · 2026-10-26