Abstract
We present Loopie, the most powerful looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6Bparameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N-fold increase in pre-training compute, increasing the parameter count by a factor of N usually outperforms looping a model N times. Loopie addresses this challenge. Extensive ablation studies, including comparisons with a vanilla 30B-A3B model, show that Loopie substantially outperforms vanilla Transformer baselines trained with the same compute budget. Our novel post-training pipeline equips Loopie with strong reasoning abilities. At the 2025 IMO and IPhO, Loopie achieves gold-medal performance without tools.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling (2026)
- Looped State-Space Language Models with Adaptive Exit-State Selection (2026)
- Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models (2026)
- Looped Transformers with Layer Normalization Provably Learn the Power Method (2026)
- Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers (2026)
- Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning (2026)
- DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper