8arXiv cs.CL (Computation and Language)·
Loopie: Looped MoE Transformer achieves gold-medal performance at IMO and IPhO
Researchers introduce Loopie, a looped Transformer series using Mixture-of-Experts architecture in two sizes (20B/2B active and 6B/0.6B active parameters). The work directly addresses the longstanding challenge that scaling parameters outperforms looping under equal compute budgets, demonstrating that Loopie substantially outperforms vanilla Transformer baselines at the same compute. A novel post-training pipeline yields strong reasoning capabilities, with Loopie achieving gold-medal performance at the 2025 IMO and IPhO competitions without tool use.
Related guides (3)
Related events (8)
Mixture of Experts (MoEs) in Transformers
A Hugging Face blog post covering Mixture of Experts (MoE) architectures as applied to transformer models. The post likely explains the technical foundations, training considerations, and practical deployment aspects of MoE models. Given the timing in early 2026, it likely contextualizes recent MoE-based frontier models and tooling support within the Hugging Face ecosystem.
Training-Free Looped Transformers: Inference-Time Recurrence via ODE-Motivated Layer Reapplication
The paper introduces a method to retrofit recurrence onto frozen pretrained transformer checkpoints at inference time by looping a contiguous mid-stack block of layers without any fine-tuning or architectural changes. Naive block reapplication degrades performance, so the authors motivate their approach by treating pre-norm transformer blocks as forward Euler ODE steps and replacing one large update with smaller damped sub-steps. Evaluated across seven model families including dense, sparse MoE, and MLA+MoE architectures, the method yields consistent benchmark improvements (e.g., +2.64 pp on MMLU-Pro for Qwen3-4B-Instruct) at no training cost.
Looped Diffusion Language Models (LoopMDM): Depth Scaling via Layer Looping
LoopMDM introduces selective looping of early-middle transformer layers in masked diffusion language models, achieving a depth-scaling effect without adding parameters. The approach matches same-size MDM performance with up to 3.3× fewer training FLOPs and outperforms deeper non-looped MDMs on reasoning benchmarks, including up to 8.5 points improvement on GSM8K. Inference-time compute scaling is enabled by varying loop counts, with adaptive loop scheduling providing additional efficiency gains. Attention analysis suggests looping works by promoting interactions among masked token positions.
Mobius Learning: cyclic depth folding enables depth-role superposition in Transformers
Researchers introduce Mobius Learning, a training architecture where different data streams follow cyclically shifted block orders in a Transformer, forcing each block group to be optimized in both shallow and deep representational roles — a property they call depth-role superposition. Experiments with a modified GPT-2 small (124M) trained on 2.5B FineWeb tokens show lower validation loss than a fixed-order looped Transformer at larger numbers of block-sequence passes. The architecture is also naturally suited to memory-constrained distributed training, as each worker stores only one block group rather than the full model stack.
LOTUS: Looped Transformers bridge latent and explicit chain-of-thought reasoning at 3B scale
Researchers introduce LOTUS (Looped Transformers with parallel supervision on latents), a latent chain-of-thought method that processes reasoning steps in hidden states rather than decoded tokens. LOTUS is claimed to be the first latent-CoT approach to match explicit CoT performance at the 3B parameter scale, while reducing thought-phase latency by 2.5x–6.9x. The method uses a looped (recurrent-depth) Transformer backbone with parallel cross-entropy supervision on gold CoT-step tokens at each latent position, and the latent space is shown to be interpretable by projecting through the base LM head to recover reasoning steps.
Expert Tying reduces MoE LLM memory footprint by ~2x with minimal quality loss
Researchers introduce Expert Tying, an architectural modification for Mixture-of-Experts LLMs that shares expert parameters across consecutive transformer layers while keeping routing and attention layer-independent. Evaluated on OLMoE, Qwen3, and DeepSeek-style MoE architectures, the method achieves nearly 2x memory reduction with negligible perplexity or downstream quality degradation. The approach exploits parameter redundancy in MoE pathways to improve the compute-to-memory trade-off for training and inference.
Program synthesis used to reverse-engineer transformer attention heads with executable Python surrogates
Researchers propose a pipeline that approximates transformer attention heads with executable Python programs generated by a language model, then re-ranked by held-out predictive accuracy. Applied to GPT-2, TinyLlama-1.1B, and Llama-3B, fewer than 1,000 programs reproduce attention patterns with >75% average IoU similarity on TinyStories. Replacing 25% of attention heads with programmatic surrogates incurs only a 16% average perplexity increase while preserving downstream QA performance, demonstrating a path toward symbolic transparency in neural models.
Global-batch Load Balancing for MoE LLM Training from Qwen
Qwen Research introduces a global-batch load balancing technique for Mixture-of-Experts (MoE) LLM training, claiming it is nearly a 'free lunch' improvement. The method addresses expert load imbalance across training batches, a known efficiency and quality bottleneck in MoE architectures. The approach targets the router and expert activation dynamics in transformer-based MoE layers.