arXiv Computation and Language September 23, 2026 By Xiaoyi Yu, Enver Sangineto, Pei Fu, Fiorenzo Parascandolo, Wenhui Tan, Ruikang Zhang, Rita Cucchiara, Ruihua Song, Jian Luan

Informed Masking: Structure-Aware Perturbation for Reinforcement Learning in Diffusion Large Language Models

Read the original on arXiv Computation and Language →

Informed Masking (IM) is a new technique for aligning Diffusion Large Language Models (dLLMs) with Reinforcement Learning (RL). It identifies a systematic upstream/downstream token structure in dLLM rollouts and shows that masking downstream tokens creates better subproblems for likelihood estimation. When integrated into three state‑of‑the‑art dLLM RL methods on LLaDA‑8B‑Instruct, IM yields up to 2.01%, 8.68%, and 5.77% relative average gains on math and planning benchmarks while improving training stability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

1d ago

On Trajectory-Aware Training for Masked Diffusion Language Models

arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...

By Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis B\'ethune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, Jo\~ao Monteiro

llms diffusion fine-tuning safety

arXiv AI

Jul 17

Mask-Aware Policy Gradients for Diffusion Language Models

arXiv:2607. 15200v1 Announce Type: cross Abstract: Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation.

By Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Kr\"ahenb\"uhl

llms diffusion reinforcement-learning benchmarks

arXiv Computation and Language

Aug 21

Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models

arXiv:2604. 18738v3 Announce Type: replace Abstract: Diffusion language models (dLLMs) generate text through iterative denoising, filling multiple masked positions at each step.

By Lin Yao

llms diffusion

arXiv AI

Jun 2

SimSD: Simple Speculative Decoding in Diffusion Language Models

arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.

By Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo, Jinya Jiang, Haoru Li, Chaojie Ren, Yiming Huang, Kaijie Zhu, Zhongkai Yu, Kun Zhou, Jingbo Shang

llms diffusion efficiency benchmarks

arXiv AI

Aug 17

CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing

arXiv:2608. 13925v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass.

By Yuji Ren, Chenkai Xu, Zhuocheng Gong, Jianguo Li, Zhijie Deng

llms diffusion efficiency safety

arXiv Machine Learning

Jun 11

Re-evaluating Confidence Remasking in Masked Diffusion Language Models

arXiv:2606. 12232v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel token generation.

By Stipe Frkovic, Metod Jazbec, Dan Zhang, Christian A. Naesseth, Ilija Bogunovic, Eric Nalisnick

llms diffusion

One email a morning, machine-written

Related stories

On Trajectory-Aware Training for Masked Diffusion Language Models

Mask-Aware Policy Gradients for Diffusion Language Models

Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models

SimSD: Simple Speculative Decoding in Diffusion Language Models

CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing

Re-evaluating Confidence Remasking in Masked Diffusion Language Models