Block-Diffusion Drafter

Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 24

All topics
CardsList

  1. LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter

    Sep 29, 2026Hao-Yuan He, Peng-Fei Liu, Si Shen +1Speculative DecodingBlock-Diffusion Drafter

  2. BV Loss: Block Verification-Aware Loss for Block Diffusion Speculative Decoding

    Sep 28, 2026Suyoung Kim, Jahyun Koo, Hyeonjin Kim +5Block-Diffusion DrafterDiffusion Language Models

    a2sys (a2sys.ai) · Seoul National University (snu.ac.kr) · University of Wisconsin (wisc.edu)

  3. Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier

    Sep 28, 2026Linye Wei, Shutian Zheng, Haoyu Zeng +1Block-Diffusion DrafterSpeculative Decoding

    Institute for Artificial Intelligence, Peking University · School of Integrated Circuits, Peking University · College of Engineering, Peking University +2

  4. Tsubame: Tree Replay for Diffusion-Based Speculative Decoding

    Sep 27, 2026Yepeng Weng, Qiao Hu, Takehisa YairiBlock-Diffusion DrafterSpeculative Decoding

    The University of Tokyo · National Center for Mathematics and Interdisciplinary Sciences (NCMIS), AMSS, CAS

  5. Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding

    Sep 22, 2026Dohyun Kim, Sungjun Han, Hyungguk Kim +4Lingdt-Vl-OcrBlock-Diffusion Drafter

    Trillion Labs · Korea University · Seoul National University

  6. H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache

    Sep 21, 2026Weifan Jiang, Krishna Teja Chitty-Venkata, Megan Flynn +6Speculative DecodingBlock-Diffusion Drafter

    Harvard University · Capital One · Red Hat +2

  7. Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding

    Aug 31, 2026Ephrem WuBlock-Diffusion DrafterDrafter

    Advanced Micro Devices, Inc., USA

  8. DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding

    Aug 5, 2026Amirmohammad Karimi, Chao Gao, Negar HassanpourSpeculative DecodingBlock-Diffusion Drafter

    Huawei Technologies Canada Co., Ltd.

  9. xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding

    Aug 3, 2026Zheng Wang, Davis Wertheimer, Yu Chin Fabian Lim +4Block-Diffusion DrafterDrafts

    University of Illinois Urbana-Champaign · IBM

  10. AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding

    Jul 28, 2026Hong Liu, Rui Cen, Junhan Shi +10Speculative DecodingBlock-Diffusion Drafter

    Tencent Inc.

  11. AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

    Jul 21, 2026Yu-Yang Qian, Hao-Cong Wu, Chen Chen +4Block-Diffusion DrafterSpeculative Decoding

    State Key Laboratory for Novel Software Technology, Nanjing University · School of Artificial Intelligence, Nanjing University · Huawei Foundation Model Dept

  12. Accepted Prefixes Are Not All You Need: A Negative Result on PEFT-Based Block-Diffusion Drafting

    Jul 14, 2026Abdurrahman Javat, Allan KazakovSpeculative DecodingBlock-Diffusion Drafter

    Bahçeşehir University, Department of Artificial Intelligence

  13. DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding

    Jul 9, 2026Saw S. Lin, Jyh-Shing Roger JangBlock-Diffusion DrafterSpeculative Decoding

    Zhiqi Zhang · Department of Computer Science and Information Engineering, National Taiwan University.

  14. Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B

    Jul 5, 2026Jaeyeon Kim, Jewon Lee, Bo-Kyeong KimLLM Inference OptimizationQwen3

    Nota Inc.

  15. JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

    Jun 16, 2026Lanxiang Hu, Zhaoxiang Feng, Yulun Wu +9Speculative DecodingBlock-Diffusion Drafter

    UC San Diego · Zhejiang University · UIUC +2

  16. Accelerating Speculative Diffusions via Block Verification

    Jun 11, 2026Alexander Soen, Hisham Husain, Valentin De Bortoli +1Block-Diffusion DrafterDiffusion Language Models

    KTH · Google Research† · Google DeepMind‡

  17. WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

    Jun 5, 2026Young D. Kwon, Miles Williams, Rui Li +2Speculative DecodingBlock-Diffusion Drafter

    Samsung AI Center, Cambridge, UK

  18. D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

    Jun 3, 2026Liyuan Zhang, Jiarui Zhang, Jinwei Yao +6Speculative DecodingBlock-Diffusion Drafter

    Peking University · Tsinghua University · HKUST +2

  19. DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding

    Jun 1, 2026Jiebin Zhang, Zhenghan Yu, Song Liu +9Block-Diffusion DrafterSpeculative Decoding

    School of Computer Science, Peking University · Tencent

  20. Cost-Aware Diffusion Draft Trees for Speculative Decoding

    Jun 1, 2026Shuai Zhang, Huachuan Qiu, Hongliang He +1Block-Diffusion DrafterSpeculative Decoding

    1Zhejiang University · 2Westlake University

  21. TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding

    May 30, 2026Zhuoyu Wang, Junnan Huang, Xinyu ChenBlock-Diffusion DrafterSpeculative Decoding

    The Hong Kong University of Science and Technology (Guangzhou)

  22. Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

    May 28, 2026Soowon Oh, Nam Cao, Yujin Kim +4Block-Diffusion DrafterSpeculative Decoding

    KAIST AI · Samsung Advanced Institute of Technology

  23. FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration

    May 19, 2026Yaojie Zhang, Jianuo Huang, Junlong Ke +5Speculative DecodingBlock-Diffusion Drafter

    EPIC Lab, SJTU · School of Software Engineering, HUST · UESTC +3

  24. D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

    May 12, 2026Tianyu Wu, Yu Yao, Zhenting Qi +7Block-Diffusion DrafterDrafter

    1Harvard · 2MIT