Diffusion Language Models

Follow this topic Ask about this topic

Recent momentum

-25%

24 papers in the last 28 days · 0.4% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

13 new papers

A weekly snapshot of new work published in Diffusion Language Models.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Diffusion Language Models.

Period ending 2026-09-07

7 new papers

A weekly snapshot of new work published in Diffusion Language Models.

268 papers

Latest in Diffusion Language Models

Browse all topics →

AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation
May 16, 2026Shiying Yu, Jielei Wang, Guoming LuRadiology Report Generation Masked Diffusion Language Models
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
May 16, 2026Fanqin Zeng, Feng Hong, Geng Yu +6Diffusion Language Models Image Denoising
Dynamic Chunking for Diffusion Language Models
May 15, 2026Yichen Zhu, Xiaoming Shi, Peng Zhao +3Diffusion Language Models Chunk
Ligand-Conditioned Discrete Diffusion for Protein Sequence-Structure Co-Design
May 15, 2026Chen Wei, Fanding Xu, Minghao Sun +5Protein Design Protein
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
May 15, 2026Shengyin Sun, Yiming Li, Renxi Liu +7Diffusion Language Models Speculative Decoding
Membership Inference Attacks on Discrete Diffusion Language Models
May 15, 2026Shailesh KasivelrajanMasked Diffusion Language Models Membership Inference Attacks
Uncertainty Quantification for Large Language Diffusion Models
May 14, 2026Artem Vazhentsev, Vladislav Smirnov, David Li +3Large Language Model Uncertainty Diffusion Language Models
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
May 14, 2026ZiYi Dong, Yuliang Huang, Weijian Deng +3Diffusion Language Models Stochastic Optimal Control
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
May 14, 2026Injin Kong, Hyoungjoon Lee, Yohan JoDiffusion Language Models Autoregressive Transformers
Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding
May 14, 2026Xun Fang, Yunchen Li, Hang Yuan +1Diffusion Language Models Speculative Decoding
Support Before Frequency in Discrete Diffusion
May 13, 2026Adrian Müller, Antoine Gonon, Zebang Shen +2Diffusion Language Models Frequency
Beyond Mode-Seeking RL: Trajectory-Balance Post-Training for Diffusion Language Models
May 13, 2026Saba Ahmadi, Prasanna Parthasarathi, Yufei CuiDiffusion Language Models LLM Post-Training Methods
Sampling from Flow Language Models via Marginal-Conditioned Bridges
May 13, 2026Iskander Azangulov, Leo ZhangGenerative Flow Networks Diffusion Language Models
BlockVLA: Accelerating Autoregressive VLA via Block Diffusion Finetuning
May 13, 2026Ruiheng Wang, Shuanghao Bai, Haoran Zhang +2Vision-Language-Action Models Diffusion Language Models
Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models
May 13, 2026Yejin Lee, Yo-Sub HanDiffusion Language Models Autoregressive Language Models
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
May 12, 2026Chien Van Nguyen, Chaitra Hegde, Van Cuong Pham +3Diffusion Language Models LLM Inference Efficiency
Multi-Token Residual Prediction
May 12, 2026Yufeng Xu, Zishuo Bao, Qian Wang +6Diffusion Language Models Next-Token Prediction
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
May 12, 2026Kecheng Chen, Ziru Liu, Xijia Tao +9Diffusion Language Models Autoregressive Language Models
Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
May 12, 2026Yan Jiang, Ruihong Qiu, Zi HuangDiffusion Language Models Training-Inference Mismatch
Language Modeling with Hyperspherical Flows
May 11, 2026Justin Deschenaux, Caglar GulcehreDiffusion Language Models Generative Flow Networks
ELF: Embedded Language Flows
May 11, 2026Keya Hu, Linlu Qiu, Yiyang Lu +5Diffusion Language Models
Infinite Mask Diffusion for Few-Step Distillation
May 11, 2026Jaehoon Yoo, Wonjung Kim, Chanhyuk Lee +1Masked Diffusion Language Models Diffusion Language Models
Relative Score Policy Optimization for Diffusion Language Models
May 11, 2026Zichao Yu, Shengze Xu, Bingqing Jiang +2Reinforcement Learning With Verifiable Reward Diffusion Language Models
TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation
May 11, 2026Wilson Wongso, Lihuan Li, Arian Prabowo +4Diffusion Language Models
Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
May 10, 2026Bian Sun, Kevin Zhai, Mubarak Shah +1Diffusion Language Models Text Generation
Edit-Based Refinement for Parallel Masked Diffusion Language Models
May 10, 2026Houxing Ren, Mingjie Zhan, Zimu Lu +5Masked Diffusion Language Models Diffusion Language Models
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
May 10, 2026Haoyang Zhou, Li Kong, Shijie Ren +4Diffusion Language Models Kullback-Leibler Divergence
Path-Dependent Denoising: A Non-Conservative Field Perspective on Order Collapse in Diffusion Language Models
May 10, 2026Jeonseong KimDiffusion Language Models Image Denoising
LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
May 9, 2026Haohui Zhang, Zhiye Wang, Xiaoying Gan +2Diffusion Language Models Parallel
Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
May 8, 2026Hanhan Zhou, Shamik Roy, Rashmi GangadharaiahDiffusion Language Models Steering
How to Train Your Latent Diffusion Language Model Jointly With the Latent Space
May 8, 2026Viacheslav Meshchaninov, Alexander Shabalin, Egor Chimbulatov +4Diffusion Language Models Latent Diffusion Model
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
May 8, 2026Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +3Conditional Flow Matching Few-Step Generation
Scaling Categorical Flow Maps
May 8, 2026Oscar Davis, Anastasiia Filippova, Pierre Ablin +4Generative Flow Networks Flow Map
TextLDM: Language Modeling with Continuous Latent Diffusion
May 8, 2026Jiaxiu Jiang, Jingjing Ren, Wenbo Li +10Diffusion Language Models Identity-Conditioned Latent Diffusion Models
GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization
May 8, 2026Yu Pan, Andi Zhang, Yi Wang +2Large Language Model Jailbreaks Diffusion Language Models
Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
May 8, 2026Weiming Chen, Xitong Ling, Zhenyang Cai +5Pathology Foundation Models Dense Prediction
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
May 8, 2026Shuai Wang, Yu Yin, Shengyao Zhuang +2Diffusion Language Models Retrievers
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
May 8, 2026Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +4Diffusion Language Models Credit Assignment
CoBit: Language Modeling with Bitstream Diffusion
May 7, 2026Georgios Batzolis, Mark Girolami, Luca AmbrogioniDiffusion Language Models Large Language Model Pretraining
Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment
May 7, 2026Fred Zhangzhi Peng, Alexis Fox, Anru R. Zhang +1Diffusion Language Models Autoregressive Language Models
Continuous Latent Diffusion Language Model
May 7, 2026Hongcan Guo, Qinyu Zhao, Yian Zhao +8Diffusion Language Models Text Generation
Layer Collapse in Diffusion Language Models
May 7, 2026Alexander Conzelmann, Albert Catalan-Tatjer, Shiwei LiuDiffusion Language Models Large Language Model Compression
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
May 6, 2026Mohd Ruhul Ameen, Akif Islam, Nadim Mahmud +1Large Language Model Watermarks Watermarking
Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
May 5, 2026Tarun Kathuria, Sachin KumarDiffusion Language Models Large Language Model Pretraining
Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs
May 5, 2026Michael Rottoli, Subhankar Roy, Stefano ParaboschiLLM Inference Efficiency Diffusion Language Models
Diffusion Masked Pretraining for Dynamic Point Cloud
May 5, 2026Zhuoyue Zhang, Jihua Zhu, Chaowei Fang +2Point Cloud Data 3D Single Object Tracking
Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
May 4, 2026Yan Jiang, Ruihong Qiu, Zi HuangDiffusion Language Models Large Language Model Reasoning
Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
May 2, 2026Jinyuan Feng, Xin Yu, Yiqun Chen +5Diffusion Language Models Contrastive Decoding
DARE: Diffusion Language Model Activation Reuse for Efficient Inference
May 1, 2026Natalia Frumkin, Bokun Wang, Hung-Yueh Chiang +3Diffusion Language Models LLM Inference Efficiency
Towards A Generative Protein Evolution Machine with DPLM-Evo
Apr 30, 2026Xinyou Wang, Liang Hong, Jiasheng Ye +4Protein Design Evolution
Consistent Diffusion Language Models
Apr 30, 2026Hasan Amin, Yuan Gao, Yaser Souri +4Diffusion Language Models Discrete Diffusion Model
Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models
Apr 29, 2026Gongbo Zhang, Wen Wang, Ye Tian +1Diffusion Language Models
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Apr 29, 2026Bao Pham, Mohammed J. Zaki, Luca Ambrogioni +2Diffusion Language Models Memorization
The Safety-Aware Denoiser for Text Diffusion Models
Apr 28, 2026Amman Yusuf, Zhejun Jiang, Mijung ParkDiffusion Language Models Autoregressive Generation
Scaling Properties of Continuous Diffusion Spoken Language Models
Apr 27, 2026Jason Ramapuram, Eeshan Gunesh Dhekane, Amitis Shidani +6Diffusion Language Models Scaling Laws
DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models
Apr 27, 2026Dake Bu, Wei Huang, Andi Han +4Diffusion Language Models Order Matters
Factual and Edit-Sensitive Graph-to-Sequence Generation via Graph-Aware Adaptive Noising
Apr 27, 2026Aditya Hemant Shahane, Anuj Kumar Sirohi, Tanmoy Chakraborty +2Diffusion Language Models Graph Language Models
When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Models
Apr 27, 2026Danny Wang, Ruihong Qiu, Zi HuangDiffusion Language Models Token-Level Uncertainty
Where to Place the Query? Unveiling and Mitigating Positional Bias in In-Context Learning for Diffusion LLMs via Decoding Dynamics
Apr 26, 2026Zhengheng Li, Panrui Li, Xuyang Liu +1In-Context Learning Diffusion Language Models
Measuring Temporal Linguistic Emergence in Diffusion Language Models
Apr 25, 2026Harry LuDiffusion Language Models Large Language Model Uncertainty

May 16, 2026 · cs.AIJ/K move · Enter open · S save

AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation

Shiying Yu, Jielei Wang, Guoming Lu

University of Electronic Science and Technology of China

Radiology report generation (RRG) aims to automatically produce clinically accurate textual reports from medical images. Existing methods predominantly rely on autoregressive (AR) language models, whose causal dependency structure restricts generation to a unidirectional left-to-right process. This paradigm can induce sequence bias, where models tend to follow stereotypical token orders and high-frequency report templates rather than fully grounding generation in image-specific evidence. In this paper, we propose AnchorDiff, the first masked-diffusion framework for RRG that integrates knowledge-graph-derived clinical anchors into diffusion language modeling. By leveraging bidirectional context and iterative refinement, AnchorDiff mitigates the limitations of fixed-order autoregressive decoding. Specifically, we introduce a topology-aware training strategy that uses RadGraph-derived entity hierarchies to assign clinically important tokens differentiated masking protection and loss weights. We further design an inference-time rewriting strategy that detects unstable committed tokens through perturbation-based testing and selectively revises them during denoising. Extensive experiments on the MIMIC-CXR and MIMIC-RG4 benchmarks demonstrate that AnchorDiff achieves state-of-the-art (SOTA) performance, showing the effectiveness of clinically anchored masked diffusion for radiology report generation.

Radiology Report Generation Masked Diffusion Language Models Diffusion Language Models Selection Bias

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

13 new papers

4 new papers

7 new papers

Latest in Diffusion Language Models