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.
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
arXiv:2610.22543v1 Announce Type: new
Abstract: Diffusion language models (DLMs) promise parallel text generation, but in practice face an unresolved speed-quality trade-off. Exact decoding fills in...
By Eliezer Shlomi, Eliron Rahimi, Avi Mendelson, Chaim Baskin
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
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.
arXiv:2607. 15655v1 Announce Type: cross Abstract: Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding.
By Yingqian Cui, Wei Deng, Lantao Mei, Hang Li, Charu C. Aggarwal, Hui Liu, Yue Xing
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
arXiv:2608.22646v1 Announce Type: new
Abstract: Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation...
By Farhana Amin, Sabiha Afroz, Dimitrios S. Nikolopoulos
Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders and parallel decoding. Recent dLLMs are often in...
Ripple-Pivot Search (RPS) is a training‑free decoding method for Diffusion Large Language Models that identifies mid‑entropy pivot positions to reduce uncertainty across remaining masked tokens. By proactively committing these pivots and evaluating token assignments via lookahead, RPS enables more tokens to be unmasked in parallel, speeding up decoding. Experiments on three dLLMs and four reasoning/code‑generation benchmarks show 4–10× wall‑clock speedup over standard decoding, up to 18× with KV caching, while maintaining or improving generation quality.
By Yushi Ye, Xu Chen, Haoyun Jiang, Jinsong Lan, Haihong Tang, Xiangtao Li, Mingming Gong, Ivor Tsang, Yanfeng Wang, Jiangchao Yao
Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding.
arXiv:2610.08108v1 Announce Type: new
Abstract: Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders...
By Yiming Qin, Ke Wang, Amel Abdelraheem, Adam Hazimeh, Pascal Frossard
The paper introduces TIPS, a tiny inference-time policy that controls which tokens are visible during each denoising pass of masked diffusion language models. TIPS, a 600‑K‑parameter shallow transformer, learns to unmask and remask tokens while keeping the language model frozen, using visibility‑aware confidence features and a fixed schedule for expected visibility. Trained via supervised warmup and reinforcement learning, TIPS achieves over 58% accuracy on GSM8K and MATH‑500 with only 32 decoder evaluations, surpassing strong baselines by more than 11 percentage points and remaining competitive at higher budgets without retraining.
By Ya-Shi Zhang, Jian Tang, Pierre-Andr\'e No\"el, Oleksiy Ostapenko