English
Related papers

Related papers: Principled Coarse-Grained Acceptance for Speculati…

200 papers

Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verification by a larger target model. In practice, speculative efficiency is often bottlenecked…

Computation and Language · Computer Science 2026-05-18 Jie Jiang , Xing Sun , Ruotian Chen , Jianan Su , Kaixin Shen

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying…

Machine Learning · Computer Science 2026-05-06 Tanishq Kumar , Tri Dao , Avner May

As the cost of pretraining large language models grows, there is continued interest in strategies to improve learning efficiency during this core training stage. Motivated by cognitive development, where humans gradually build knowledge as…

Computation and Language · Computer Science 2026-02-10 Karanpartap Singh , Neil Band , Ehsan Adeli

Spurred by the demand for interpretable models, research on eXplainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP…

Computation and Language · Computer Science 2025-03-18 Dennis Fucci , Marco Gaido , Beatrice Savoldi , Matteo Negri , Mauro Cettolo , Luisa Bentivogli

Recently, speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small draft model to propose draft tokens in advance, and validating them in parallel with the large target model. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-15 Yuhao Shen , Junyi Shen , Quan Kong , Tianyu Liu , Yao Lu , Cong Wang

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model…

Computation and Language · Computer Science 2025-10-09 Yunhai Hu , Zining Liu , Zhenyuan Dong , Tianfan Peng , Bradley McDanel , Sai Qian Zhang

A recurring pattern in "reasoning without training" is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the bottleneck is locating these modes efficiently at inference time. Power sampling provides…

Artificial Intelligence · Computer Science 2026-05-13 Tu Nguyen , Matthieu Zimmer , Rasul Tutunov , Xiaotong Ji , Haitham Bou Ammar

Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints. Existing approaches to constrained generation fall along a spectrum: greedy constrained decoding…

Artificial Intelligence · Computer Science 2025-10-03 Paweł Parys , Sairam Vaidya , Taylor Berg-Kirkpatrick , Loris D'Antoni

In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large…

Computation and Language · Computer Science 2024-02-12 Aliakbar Nafar , Kristen Brent Venable , Parisa Kordjamshidi

Speculative Decoding is a widely used technique to speed up inference for Large Language Models (LLMs) without sacrificing quality. When performing inference, speculative decoding uses a smaller draft model to generate speculative tokens…

Machine Learning · Computer Science 2025-02-06 Minghao Yan , Saurabh Agarwal , Shivaram Venkataraman

Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing…

Computation and Language · Computer Science 2026-03-25 Debashish Chakraborty , Eugene Yang , Daniel Khashabi , Dawn Lawrie , Kevin Duh

Parameter-efficient fine-tuning (PEFT) of vision-language models (VLMs) excels in various vision tasks thanks to the rich knowledge and generalization ability of VLMs. However, recent studies revealed that such fine-tuned VLMs are…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Nayeong Kim , Seong Joon Oh , Suha Kwak

Speculative decoding has been widely used to accelerate auto-regressive (AR) text generation. However, its effectiveness for visual AR models remains limited due to token selection ambiguity, where multiple tokens share similarly low…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Sihwan Park , Doohyuk Jang , Sungyub Kim , Souvik Kundu , Eunho Yang

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

Computation and Language · Computer Science 2024-10-15 Yunsheng Ni , Chuanjian Liu , Yehui Tang , Kai Han , Yunhe Wang

Recently, autoregressive (AR) image models have demonstrated remarkable generative capabilities, positioning themselves as a compelling alternative to diffusion models. However, their sequential nature leads to long inference times,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Junhyuk So , Juncheol Shin , Hyunho Kook , Eunhyeok Park

Sampling-based decoding underlies complex reasoning in large language models (LLMs), where decoding strategies critically shape model behavior. Temperature- and truncation-based methods reshape the next-token distribution through global…

Artificial Intelligence · Computer Science 2026-02-02 Yixin Yang , Qingxiu Dong , Zhifang Sui

Probabilistic Circuits (PCs) are deep generative models that support exact and efficient probabilistic inference. Yet in autoregressive language modeling, PCs still lag behind Transformer-based large language models (LLMs), suggesting an…

Machine Learning · Computer Science 2026-05-14 Zhiyu Zhao , Xuejie Liu , Muhan Zhang , Anji Liu

Speculative decoding has emerged as a promising approach to accelerate inference in vision-language models (VLMs) by enabling parallel verification of multiple draft tokens. However, existing methods rely on static tree structures that…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Yujia Tong , Tian Zhang , Yunyang Wan , Kaiwei Lin , Jingling Yuan , Chuang Hu

Coarse-graining has become an area of tremendous importance within many different research fields. For molecular simulation, coarse-graining bears the promise of finding simplified models such that long-time simulations of large-scale…

Chemical Physics · Physics 2019-09-04 Feliks Nüske , Lorenzo Boninsegna , Cecilia Clementi

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently…

Computation and Language · Computer Science 2025-09-08 Shengyin Sun , Yiming Li , Xing Li , Yingzhao Lian , Weizhe Lin , Hui-Ling Zhen , Zhiyuan Yang , Chen Chen , Xianzhi Yu , Mingxuan Yuan , Chen Ma