arXiv:2606. 04236v1 Announce Type: cross Abstract: Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off.
By Giries Abu Ayoub, Mario Barbara, Llu\'is Pastor-P\'erez, Tanja Bien, Aneesh Barthakur, Alaa Maalouf, Loay Mualem
arXiv:2606. 15805v1 Announce Type: new Abstract: Discrete diffusion language models enable parallel token generation, offering a pathway to low-latency decoding.
By Tamim Zoabi, Ameen Ali, Liran Ringel, Lior Wolf
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
TeCoP is a training‑free decoder that accelerates diffusion large language model (dLLM) decoding by decoupling prediction readiness from context utility. It uses tentative context pipelining and draft‑and‑verify to reuse stable but uncommitted predictions as provisional cross‑block context, with commitment based on confidence and stability checks. Across four dLLMs on GSM8K, Minerva MATH, and MBPP, TeCoP cuts forward evaluations by up to 87% and boosts throughput up to 7.5‑fold without KV caching and 11.77‑fold with caching, outperforming Fast‑dLLM and DSB while maintaining accuracy within one percentage point.
By Jui-Chien Tsou, Hsuan-Chi Liu, Wei-Chin Wang, Yu-Syuan Xu, Chun-Yi Lee
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:2609.37391v1 Announce Type: new
Abstract: Diffusion language models (DLMs) enable parallel generation by predicting and committing multiple tokens at each denoising step, yet they can generate...
By Kodai Kawamura, Kenji Kawaguchi, Anji Liu
arXiv:2606. 02955v3 Announce Type: replace-cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.
By Siva Rajesh Kasa, Yasong Dai, Sumit Negi, Hongdong Li
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
Masked Diffusion Models (MDMs) generate text quickly through parallel decoding but can commit to inconsistent predictions. The paper introduces PURL, a training framework that unifies parallel generation with selective token revision by learning a joint transition over edit selection, unmask selection, and token prediction. Experiments on logic puzzles, mathematical reasoning, and code generation show PURL improves accuracy by up to 47.4% and reduces decoding rounds by up to eightfold, while revealing that effective revisions depend on timing and context.
By Haoyang Zheng, Yidong Ouyang, Blake Jianhang Chen, Tian Tan, Ziqian Lin, Liqian Peng, Alec Go, Guang Lin
Diffusion language models accelerate generation by decoding multiple masked positions per forward pass. However, accuracy is known to drop when parallel decoding trajectories deviate from their sequen...
arXiv:2606. 02955v1 Announce Type: cross Abstract: Diffusion large language models promise parallel token generation, yet inference remains bottlenecked by deciding which masked tokens can be safely committed together.
By Siva Rajesh Kasa, Yasong Dai, Sumit Negi, Hongdong Li
The paper introduces DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores intra-block dependencies in speculative decoding by evaluating multiple candidate tokens for contextual compatibility across adjacent draft positions. DCOCO maintains parallel drafting while enabling contextually informed token selection at low additional cost. Across multiple verifier backbones and benchmarks, DCOCO achieves the highest average throughput, delivering speedups of up to 6.6× over vanilla decoding and outperforming competing methods by 6–23% under concurrent serving loads.
By Roy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman