Fetching the paper…
Reading the bibliography…
Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored.
Fast r-cnn
Ross Girshick · 2015
Earlier work this paper cites.
Fitnets: Hints for thin deep nets, 2015
Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio · 2015
Earlier work this paper cites.
Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer
Sergey Zagoruyko and Nikos Komodakis · 2017
Earlier work this paper cites.
Blockwise parallel decoding for deep autoregressive models
Mitchell Stern, Noam Shazeer, and Jakob Uszkoreit · 2018
Earlier work this paper cites.
Contrastive distillation on intermediate representations for language model compression
Siqi Sun, Zhe Gan, Yuwei Fang, Yu Cheng, Shuohang Wang, and Jingjing Liu · 2020
Earlier work this paper cites.
Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation
Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi · 2022
Earlier work this paper cites.
Learn to explain: Multimodal reasoning via thought chains for science question answering
Pan Lu, Swaroop Mishra, Tony Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan · 2022
Earlier work this paper cites.
ChartQA: A benchmark for question answering about charts with visual and logical reasoning
Ahmed Masry, Do Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque · 2022
Earlier work this paper cites.
Accelerating large language model decoding with speculative sampling
Charlie Chen, Sebastian Borgeaud, Geoffrey Irving, Jean-Baptiste Lespiau, Laurent Sifre, and John Jumper · 2023
Earlier work this paper cites.
Instructblip: towards general-purpose vision-language models with instruction tuning
Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi · 2023
Earlier work this paper cites.
Rest: Retrieval-based speculative decoding
Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D Lee, and Di He · 2023
Earlier work this paper cites.
Speed: Speculative pipelined execution for efficient decoding
Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Hasan Genc, Kurt Keutzer, Amir Gholami, and Sophia Shao · 2023
Earlier work this paper cites.
Fast inference from transformers via speculative decoding
Yaniv Leviathan, Matan Kalman, and Yossi Matias · 2023
Earlier work this paper cites.
Seed-bench-2: Benchmarking multimodal large language models
Bohao Li, Yuying Ge, Yixiao Ge, Guangzhi Wang, Rui Wang, Ruimao Zhang, and Ying Shan · 2023
Earlier work this paper cites.
Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models
Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi · 2023
Earlier work this paper cites.
Less is more: task-aware layer-wise distillation for language model compression
Chen Liang, Simiao Zuo, Qingru Zhang, Pengcheng He, Weizhu Chen, and Tuo Zhao · 2023
Earlier work this paper cites.
Improved baselines with visual instruction tuning, 2023
Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee · 2023
Earlier work this paper cites.
Visual instruction tuning
Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee · 2023
Earlier work this paper cites.
Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, et al · 2023
Earlier work this paper cites.
Pass: Parallel speculative sampling
Giovanni Monea, Armand Joulin, and Edouard Grave · 2023
Earlier work this paper cites.
Accelerating transformer inference for translation via parallel decoding
Andrea Santilli, Silvio Severino, Emilian Postolache, Valentino Maiorca, Michele Mancusi, Riccardo Marin, and Emanuele Rodolà · 2023
Earlier work this paper cites.
Accelerating llm inference with staged speculative decoding
Benjamin Spector and Chris Re · 2023
Cited alongside, same era.
Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation
Heming Xia, Tao Ge, Peiyi Wang, Si-Qing Chen, Furu Wei, and Zhifang Sui · 2023
Cited alongside, same era.
Inference with reference: Lossless acceleration of large language models
Nan Yang, Tao Ge, Liang Wang, Binxing Jiao, Daxin Jiang, Linjun Yang, Rangan Majumder, and Furu Wei · 2023
Cited alongside, same era.
Tinygpt-v: Efficient multimodal large language model via small backbones
Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye, and Lichao Sun · 2023
Cited alongside, same era.
Draft & verify: Lossless large language model acceleration via self-speculative decoding
Jiahao Liu, Qifan Wang, Jingang Wang, and Xunliang Cai · 2024
Later among the works it cites.
Parallel speculative decoding with adaptive draft length
Tianyu Liu, Yun Li, Qitan Lv, Kai Liu, Jianchen Zhu, and Winston Hu · 2024
Later among the works it cites.
Adaptive draft-verification for efficient large language model decoding
Xukun Liu, Bowen Lei, Ruqi Zhang, and Dongkuan Xu · 2024
Later among the works it cites.
Ocrbench: on the hidden mystery of ocr in large multimodal models
Yuliang Liu, Zhang Li, Mingxin Huang, Biao Yang, Wenwen Yu, Chunyuan Li, Xu-Cheng Yin, Cheng-Lin Liu, Lianwen Jin, and Xiang Bai · 2024
Later among the works it cites.
Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Jun Zhang, Jue Wang, Huan Li, Lidan Shou, Ke Chen, Gang Chen, and Sharad Mehrotra · 2023
Cited alongside, same era.
Distillspec: Improving speculative decoding via knowledge distillation
Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-François Kagy, and Rishabh Agarwal · 2023
Cited alongside, same era.
Pravesh Agrawal, Szymon Antoniak, Emma Bou Hanna, Baptiste Bout, Devendra Chaplot, Jessica Chudnovsky, Diogo Costa, Baudouin De Monicault, Saurabh Garg, Theophile Gervet, et al · 2024
Cited alongside, same era.
Hydra: Sequentially-dependent draft heads for medusa decoding
Zachary Ankner, Rishab Parthasarathy, Aniruddha Nrusimha, Christopher Rinard, Jonathan Ragan-Kelley, and William Brandon · 2024
Cited alongside, same era.
Paligemma: A versatile 3b vlm for transfer
Lucas Beyer, Andreas Steiner, André Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, et al · 2024
Cited alongside, same era.
Medusa: Simple llm inference acceleration framework with multiple decoding heads
Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D Lee, Deming Chen, and Tri Dao · 2024
Cited alongside, same era.
Sequoia: Scalable, robust, and hardware-aware speculative decoding
Zhuoming Chen, Avner May, Ruslan Svirschevski, Yuhsun Huang, Max Ryabinin, Zhihao Jia, and Beidi Chen · 2024
Cited alongside, same era.
Layer skip: Enabling early exit inference and self-speculative decoding
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, et al · 2024
Cited alongside, same era.
Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao · 2024
Later among the works it cites.
Lossless acceleration of large language model via adaptive n-gram parallel decoding
Jie Ou, Yueming Chen, and Wenhong Tian · 2024
Later among the works it cites.
Faster speech-llama inference with multi-token prediction
Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, and Ozlem Kalinli · 2024
Later among the works it cites.
The n-grammys: Accelerating autoregressive inference with learning-free batched speculation
Lawrence Stewart, Matthew Trager, Sujan Kumar Gonugondla, and Stefano Soatto · 2024
Later among the works it cites.
Triforce: Lossless acceleration of long sequence generation with hierarchical speculative decoding
Hanshi Sun, Zhuoming Chen, Xinyu Yang, Yuandong Tian, and Beidi Chen · 2024
Later among the works it cites.
Spectr: Fast speculative decoding via optimal transport
Ziteng Sun, Ananda Theertha Suresh, Jae Hun Ro, Ahmad Beirami, Himanshu Jain, and Felix Yu · 2024
Later among the works it cites.
Speculative rag: Enhancing retrieval augmented generation through drafting
Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, et al · 2024
Later among the works it cites.
Swift: On-the-fly self-speculative decoding for llm inference acceleration
Heming Xia, Yongqi Li, Jun Zhang, Cunxiao Du, and Wenjie Li · 2024
Later among the works it cites.
Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi, 2024
Kaining Ying, Fanqing Meng, Jin Wang, Zhiqian Li, Han Lin, Yue Yang, Hao Zhang, Wenbo Zhang, Yuqi Lin, Shuo Liu, Jiayi Lei, Quanfeng Lu, Runjian Chen, Peng Xu, Renrui Zhang, Haozhe Zhang, Peng Gao, Yali Wang, Yu Qiao, Ping Luo, Kaipeng Zhang, and Wenqi Shao · 2024
Later among the works it cites.
Dovetail: A cpu/gpu heterogeneous speculative decoding for llm inference
Libo Zhang, Zhaoning Zhang, Baizhou Xu, Songzhu Mei, and Dongsheng Li · 2024
Later among the works it cites.
Tinyllava: A framework of small-scale large multimodal models
Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, and Lei Huang · 2024
Later among the works it cites.
Speculative decoding and beyond: An in-depth survey of techniques
Yunhai Hu, Zining Liu, Zhenyuan Dong, Tianfan Peng, Bradley McDanel, and Sai Qian Zhang · 2025
Closest in time.
Eagle-3: Scaling up inference acceleration of large language models via training-time test
Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang · 2025
Closest in time.
Smolvlm: Redefining small and efficient multimodal models
Andrés Marafioti, Orr Zohar, Miquel Farré, Merve Noyan, Elie Bakouch, Pedro Cuenca, Cyril Zakka, Loubna Ben Allal, Anton Lozhkov, Nouamane Tazi, Vaibhav Srivastav, Joshua Lochner, Hugo Larcher, Mathieu Morlon, Lewis Tunstall, Leandro von Werra, and Thomas Wolf · 2025
Closest in time.
Layer by layer: Uncovering hidden representations in language models, 2025
Oscar Skean, Md Rifat Arefin, Dan Zhao, Niket Patel, Jalal Naghiyev, Yann LeCun, and Ravid Shwartz-Ziv · 2025
Closest in time.
Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, et al · 2025
Closest in time.