Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing

Hanchi Sun, Yixin Liu, Yonghui Wu, Lichao Sun

Expert Threshold Routing for Autoregressive Language Modeling with Dynamic Computation Allocation and Load Balancing: 10 upvotes on Hugging Face Daily Papers, #20 of 33 papers on 2026-03-19. Day-by-day upvote history.

Token-choice Mixture-of-Experts (TC-MoE) routes each token to a fixed number of experts, limiting dynamic computation allocation and requiring auxiliary losses to maintain load balance. We propose Expert Threshold (ET) routing, where each expert maintains an exponential moving average (EMA) threshold estimated from the global token distribution. At both training and inference, each token is independently routed to an expert if its score exceeds the expert's threshold, enabling dynamic computation allocation while achieving load balance without auxiliary losses. This fully causal mechanism eliminates dependence on other tokens in the batch, making it well-suited for autoregressive language modeling. In pretraining experiments scaling to 2.4B parameters on FineWeb-Edu, ET achieves 0.067 lower cross-entropy loss than TC-MoE, equivalent to reaching the same performance with 1.6times fewer tokens.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.