{"ID":2831675,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.07503","arxiv_id":"2512.07503","title":"SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation","abstract":"Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token prediction during inference. To accelerate autoregressive text-to-image generation, we propose Speculative Jacobi Decoding++ (SJD++), a training-free probabilistic parallel decoding algorithm. Unlike traditional next-token prediction, SJD++ performs multi-token prediction in each forward pass, drastically reducing generation steps. Specifically, it integrates the iterative multi-token prediction mechanism from Jacobi decoding, with the probabilistic drafting-and-verification mechanism from speculative sampling. More importantly, for further acceleration, SJD++ reuses high-confidence draft tokens after each verification phase instead of resampling them all. We conduct extensive experiments on several representative autoregressive text-to-image generation models and demonstrate that SJD++ achieves $2\\times$ to $3\\times$ inference latency reduction and $2\\times$ to $7\\times$ step compression, while preserving visual quality with no observable degradation.","short_abstract":"Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token prediction during inference. To accelerate autoregressive text-to-image generation, we propose Speculative J...","url_abs":"https://arxiv.org/abs/2512.07503","url_pdf":"https://arxiv.org/pdf/2512.07503v1","authors":"[\"Yao Teng\",\"Zhihuan Jiang\",\"Han Shi\",\"Xian Liu\",\"Xuefei Ning\",\"Guohao Dai\",\"Yu Wang\",\"Zhenguo Li\",\"Xihui Liu\"]","published":"2025-12-08T12:36:43Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}