arXiv Machine Learning October 16, 2026 By Yifan Yu, Yuqing Jian, Jisen Li, Yuezhou Hu, Tianyi Zhang, Xiaoxia Wu, Rui-Jie Zhu, Junxiong Wang, Zhongzhu Zhou, Fan Lai, James Zou, Chenfeng Xu

On-Policy Residual Learning for Diffusion Language Models

Read the original on arXiv Machine Learning →

On-Policy Residual Learning for Diffusion Language Models (ORL) introduces a framework that learns residual context directly from model-generated trajectories, using an entropy-contraction objective to sharpen predictions. The approach co-designs algorithmic and system components—such as asynchronous residual capture, block-diffusion attention, and packed compute-balanced training—to enable practical scaling. Experiments on a 4B DLM converted from Qwen3-4B show up to 6.2× faster tokens per forward and 6.9× higher end-to-end throughput, while also improving speed-quality trade-offs over autoregressive models and transferring effectively to other DLMs like LLaDA-2.1-mini and DiffusionGemma.

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 Machine Learning.

arXiv AI

Sep 30

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

Aug 13

CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

arXiv:2608. 11235v1 Announce Type: new Abstract: Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon.

By Yifan Wu, Yufeng Zhang, Kenli Li

llms diffusion benchmarks

Hugging Face Trending Papers

Jul 20

FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models

Block-wise diffusion large language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly serial. Prior work has attempted to unlock inter-block parallelism through post-training methods, but achieves only modest speedups and often degrades accuracy.

llms diffusion efficiency benchmarks

arXiv Machine Learning

Sep 4

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

arXiv:2609. 04010v1 Announce Type: new Abstract: Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation.

By Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham, Jonathan Geuter, Chaitanya Dwivedi, Varad Pimpalkhute, Yash Akhauri, Alexander Moreno, Mikhail Yurochkin, Zhenting Wang, Mostafa Elhoushi, Nolan Dey, Shane Bergsma, Joel Hestness, John Thickstun, Eric Xing, Zhengzhong Liu

llms agents diffusion efficiency benchmarks

arXiv AI

Jun 8

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

arXiv:2606. 06712v1 Announce Type: cross Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs).

By Xingyu Su, Jacob Helwig, Shubham Parashar, Atharv Chagi, Lakshmi Jotsna, Degui Zhi, James Caverlee, Dileep Kalathil, Shuiwang Ji

llms diffusion efficiency

arXiv AI

Jul 21

FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models

arXiv:2607. 17652v1 Announce Type: new Abstract: Block-wise diffusion large language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly serial.

By Bing Tian, Haikun Liu, Xiaocheng Zhong, Zhuohui Duan, Zhaokai Luo, Huayi Jin, Zhiyong Wang, Xiaofei Liao

llms diffusion efficiency benchmarks

One email a morning, machine-written

Related stories

On Trajectory-Aware Training for Masked Diffusion Language Models

CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

FlowBlock: Wavefront-Parallel Decoding for Self-Correcting Diffusion Language Models