This work analyzes the optimal design of the subtokenizer that minimizes MDM-Prime training objective and develops MDM-Prime-v2, a masked diffusion language model which incorporates Binary Encoding and Index Shuffling.
Abstract
Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens into sub-tokens and models the diffusion process at the sub-token level. We identify two limitations of the MDM-Prime framework. First, we find that the functional form of the subtokenizer significantly increases the cross-entropy loss in the objective when paired with commonly used Byte-Pair-Encoding (BPE) tokenizers. Second, we lack tools to guide the hyperparameter choice of the token granularity in the subtokenizer. To address these limitations, we analyze the optimal design of the subtokenizer that minimizes MDM-Prime training objective and develop MDM-Prime-v2, a masked diffusion language model which incorporates Binary Encoding and Index Shuffling. Our analysis characterizes how token granularity and sub-token entropy influence the training objective and downstream performance, providing principled criteria for subtokenizer design. When extending the model size to 1.1B parameters, MDM-Prime-v2 demonstrates superior average zero-shot accuracy across eight commonsense reasoning benchmarks, outperforming similar-sized baselines including GPT-Neo, OPT, Pythia, Bloom, SMDM, and TinyLLaMA.
GoldiMask is introduced, which selects tokens to reveal as context by approximately maximizing a submodular objective and weights the remaining targets according to how they benefit from the selected context and their remaining learning potential.
L. Mualem, L. Pastor-Pérez, Vinh Tong et al.· arXiv.org· 0 citations
Discrete diffusion language models can generate multiple tokens in parallel, but reducing the number of denoising steps can lead to inconsistent predictions. Standard cross-entropy training fits conditional token marginals, whereas parallel generation requires consistent joint predictions. We introduce Alpha Diffusion...
N. Gushchin, D. Baranchuk, Alexander Korotin· arXiv.org· 3 citations· ⚡1
This design introduces a rewritable proposal that uses additional compute to improve expressivity while keeping the simple mask-based transition schedule of MDMs, and fine-tune Qwen2.5-7B and Qwen3-8B to obtain LED-\texttt{7B} and LED-\texttt{8B}, respectively.
Yu-Yan Zhou, Ze-Yuan Yang, Yuxuan Song et al.· 0 citations
Zarya is introduced, a family of hybrid language models that jointly optimizes an autoregressive (AR) objective and a masked-diffusion objective within a single architecture, demonstrating performance on standard benchmarks while offering a principled integration of autoregressive and diffusion paradigms.
Leonid S. Sinev, Ilya Koziev, Vladislav Leshchuk· arXiv.org· 0 citations
A single evaluation score can rank generation systems but rarely reveals what failed. We propose rate-resolved text evaluation, which turns the masking rate of masked diffusion language models into a diagnostic axis. By reconstructing text under different fractions of masked tokens, one diffusion score becomes a vector...
Yiqi Liu, Kun Zhao, Cheng-Hua Lin et al.· 0 citations
Continuous diffusion language models generate all tokens in parallel, yet high-quality generation can still require hundreds of network evaluations (NFEs). We study how distributional distillation can reduce this cost by exploiting the student's probabilistic token outputs. Our unified formulation connects the student'...
Paul Le Van Kiem, Dario Shariatian, Umut Simsekli et al.· arXiv.org· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026