T-LoopFormer: Token-Level Elastic-Depth Looped Transformers with Dynamic Routing
Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across multiple iterations, achieving parameter efficiency without sacrificing representational power. Besides, looped Transformers perform inference directly in the latent space (latent reasoning) to reduce the number of tokens consumed during inference, thereby achieving improved sample efficiency. However, these models typically apply a fixed recursion depth uniformly to every token, leading to suboptimal compute allocation and leaving significant efficiency gains on the table. In this work, we propose \textbf{t}oken-level elastic-depth \textbf{lo...
| Authors | Mingqian Yu, Wenpeng Zhang, Shaobo Cui et al. |
|---|---|
| Primary category | cs.AI |
| Published | 14 September 2026 |
| Last updated at source | 14 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.