English
Related papers

Related papers: KOALA: Enhancing Speculative Decoding for LLM via …

200 papers

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

Artificial Intelligence · Computer Science 2024-11-25 Haolin Chen , Yihao Feng , Zuxin Liu , Weiran Yao , Akshara Prabhakar , Shelby Heinecke , Ricky Ho , Phil Mui , Silvio Savarese , Caiming Xiong , Huan Wang

Although speculative decoding is widely used to accelerate Vision-Language Models (VLMs) inference, it faces severe performance collapse when applied to Video Large Language Models (Vid-LLMs). The draft model typically falls into the trap…

Computer Vision and Pattern Recognition · Computer Science 2026-02-18 Libo Zhang , Zhaoning Zhang , Wangyang Hong , Peng Qiao , Dongsheng Li

Recent unified multimodal large language models (MLLMs) have shown impressive capabilities, incorporating chain-of-thought (CoT) reasoning for enhanced text-to-image generation. However, existing approaches remain limited, either treating…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Dongzhi Jiang , Renrui Zhang , Haodong Li , Zhuofan Zong , Ziyu Guo , Jun He , Claire Guo , Junyan Ye , Rongyao Fang , Weijia Li , Rui Liu , Hongsheng Li

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

Large Language Model (LLM) collaborative decoding techniques improve output quality by combining the outputs of multiple models at each generation step, but they incur high computational costs. In this paper, we introduce Collaborative…

Computation and Language · Computer Science 2025-05-30 Jiale Fu , Yuchu Jiang , Junkai Chen , Jiaming Fan , Xin Geng , Xu Yang

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

Computation and Language · Computer Science 2025-06-03 Mike Lasby , Nish Sinnadurai , Valavan Manohararajah , Sean Lie , Yani Ioannou , Vithursan Thangarasa

Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as each step necessitates moving the full model parameters…

Machine Learning · Computer Science 2024-06-18 Tianle Cai , Yuhong Li , Zhengyang Geng , Hongwu Peng , Jason D. Lee , Deming Chen , Tri Dao

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

Machine Learning · Computer Science 2025-10-31 Qiaoling Chen , Zijun Liu , Peng Sun , Shenggui Li , Guoteng Wang , Ziming Liu , Yonggang Wen , Siyuan Feng , Tianwei Zhang

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally…

Machine Learning · Computer Science 2026-05-25 Miria Feng , Mert Pilanci

Large Language Models (LLMs) are pivotal in advancing natural language processing but often struggle with complex reasoning tasks due to inefficient attention distributions. In this paper, we explore the effect of increased computed tokens…

Computation and Language · Computer Science 2024-06-25 Bingli Liao , Danilo Vasconcellos Vargas

In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, current MLLMs are composed of the well-known…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Han Zhao , Min Zhang , Wei Zhao , Pengxiang Ding , Siteng Huang , Donglin Wang

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of tokens generated by the draft model at each iteration. In…

Computation and Language · Computer Science 2024-11-08 Jonathan Mamou , Oren Pereg , Daniel Korat , Moshe Berchansky , Nadav Timor , Moshe Wasserblat , Roy Schwartz

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine Learning · Computer Science 2026-02-20 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Hao Sun , Chenliang Xu , Jianfeng Gao

Recent efforts have augmented large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning, leading to a new class of language agents.…

Artificial Intelligence · Computer Science 2024-03-18 Theodore R. Sumers , Shunyu Yao , Karthik Narasimhan , Thomas L. Griffiths

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of…

Machine Learning · Computer Science 2025-10-10 Yeskendir Koishekenov , Aldo Lipani , Nicola Cancedda

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Optimization is often cast as a deterministic problem, where the solution is found through some iterative procedure such as gradient descent. However, when training neural networks the loss function changes over (iteration) time due to the…

Machine Learning · Computer Science 2025-03-25 Aram Davtyan , Sepehr Sameni , Llukman Cerkezi , Givi Meishvilli , Adam Bielski , Paolo Favaro

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

Large Language Models have demonstrated remarkable abilities in reasoning and planning by breaking down complex problems into sequential steps. Despite their success in various domains like mathematical problem-solving and coding, LLMs face…

Artificial Intelligence · Computer Science 2024-10-29 Chang Ma , Haiteng Zhao , Junlei Zhang , Junxian He , Lingpeng Kong