English
Related papers

Related papers: SD$^2$: Self-Distilled Sparse Drafters

200 papers

Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Qitan Lv , Tianyu Liu , Wen Wu , Xuenan Xu , Bowen Zhou , Feng Wu , Chao Zhang

Generating diverse responses is crucial for test-time scaling of large language models (LLMs), yet standard stochastic sampling mostly yields surface-level lexical variation, limiting semantic exploration. In this paper, we propose…

Computation and Language · Computer Science 2026-04-29 Yuanhao Zeng , Ao Lu , Lufei Li , Zheng Zhang , Yexin Li , Kan Ren

The synergistic mechanism based on Speculative Decoding (SD) has garnered considerable attention as a simple yet effective approach for accelerating the inference of large language models (LLMs). Nonetheless, the high rejection rates…

Computation and Language · Computer Science 2025-06-04 Chuanghao Ding , Jiaping Wang , Ziqing Yang , Xiaoliang Wang , Dahua Lin , Cam-Tu Nguyen , Fei Tan

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Computation and Language · Computer Science 2026-04-09 Penghui Yang , Cunxiao Du , Fengzhuo Zhang , Haonan Wang , Tianyu Pang , Chao Du , Bo An

We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models. We present a new method called self-distilled quantization (SDQ) that minimizes accumulative…

Computation and Language · Computer Science 2023-07-13 James O' Neill , Sourav Dutta

Speculative decoding is a powerful technique that accelerates Large Language Model (LLM) inference by leveraging a lightweight speculative draft model. However, existing designs suffers in performance due to misalignment between training…

Computation and Language · Computer Science 2025-05-27 Yepeng Weng , Dianwen Mei , Huishi Qiu , Xujie Chen , Li Liu , Jiang Tian , Zhongchao Shi

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low…

Artificial Intelligence · Computer Science 2023-08-10 Benjamin Spector , Chris Re

Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by verifying multiple tokens within a single forward pass, which…

Computation and Language · Computer Science 2025-05-30 Yudi Zhang , Weilin Zhao , Xu Han , Tiejun Zhao , Wang Xu , Hailong Cao , Conghui Zhu

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often…

Computation and Language · Computer Science 2026-03-06 Ofir Ben Shoham

Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturbation and long-context inputs. We identify a previously-unreported phenomenon we call…

Machine Learning · Computer Science 2026-05-12 Doğaç Eldenk , Payal Mohapatra , Yigitcan Comlek , Kaan Oktay , Hongyang Zhang , Stephen Xia

Speculative decoding relies on fast and accurate drafters. Recent state-of-the-art language models employ larger and larger vocabularies, which significantly slows down drafters. One promising approach to boost the efficiency of speculative…

Machine Learning · Computer Science 2025-06-05 Nadav Timor , Jonathan Mamou , Oren Pereg , Hongyang Zhang , David Harel

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…

Computation and Language · Computer Science 2024-08-26 Phuc Phan , Hieu Tran , Long Phan

Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enforces the generated distribution to match that of the…

Machine Learning · Computer Science 2026-04-08 Yongchang Hao , Lili Mou

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token generation rates. However, currently available open-source dLLMs often…

Machine Learning · Computer Science 2026-01-15 Sudhanshu Agrawal , Risheek Garrepalli , Raghavv Goel , Mingu Lee , Christopher Lott , Fatih Porikli

Knowledge distillation plays a key role in compressing the Large Language Models (LLMs), which boosts a small-size student model under large teacher models' guidance. However, existing LLM distillation methods overly rely on…

Computation and Language · Computer Science 2024-07-16 Xiaoyu Liu , Yun Zhang , Wei Li , Simiao Li , Xudong Huang , Hanting Chen , Yehui Tang , Jie Hu , Zhiwei Xiong , Yunhe Wang

Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from frequent false rejections, particularly when draft models produce semantically correct but…

Computation and Language · Computer Science 2026-04-16 Xuwen Zhou , Fangxin Liu , Chao Wang , Xiao Zheng , Hao Zheng , Min He , Li Jiang , Haibing Guan

Diffusion large language models (dLLMs) generate text by iteratively denoising masked token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iterations still makes…

Computation and Language · Computer Science 2026-05-18 Shengyin Sun , Yiming Li , Renxi Liu , Xinqi Li , Hui-Ling Zhen , Weizhe Lin , Chen Chen , Xianzhi Yu , Mingxuan Yuan , Chen Ma

Identifying wireless modulation schemes is essential for cognitive radio, but standard supervised models often degrade under distribution shift, and training domain-specific wireless foundation models from scratch is computationally…

Machine Learning · Computer Science 2026-03-30 Mohammad Rostami , Atik Faysal , Reihaneh Gh. Roshan , Huaxia Wang , Nikhil Muralidhar , Yu-Dong Yao

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of…

Computation and Language · Computer Science 2024-04-16 Mukul Gagrani , Raghavv Goel , Wonseok Jeon , Junyoung Park , Mingu Lee , Christopher Lott