English
Related papers

Related papers: REST: Retrieval-Based Speculative Decoding

200 papers

Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a…

Machine Learning · Computer Science 2026-01-29 Rui Pan , Zhuofu Chen , Hongyi Liu , Arvind Krishnamurthy , Ravi Netravali

Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its token-centric nature allows erroneous steps to propagate.…

Computation and Language · Computer Science 2026-04-17 Kiran Purohit , Ramasuri Narayanam , Soumyabrata Pal

Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences. Existing eviction methods typically retain KV pairs with…

Computation and Language · Computer Science 2026-05-12 Yongqi An , Chang Lu , Kuan Zhu , Tao Yu , Chaoyang Zhao , Hong Wu , Ming Tang , Jinqiao Wang

We introduce the structured scene-text spotting task, which requires a scene-text OCR system to spot text in the wild according to a query regular expression. Contrary to generic scene text OCR, structured scene-text spotting seeks to…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Sergi Garcia-Bordils , Dimosthenis Karatzas , Marçal Rusiñol

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…

Computation and Language · Computer Science 2025-11-14 Bo Li , Zhenghua Xu , Rui Xie

Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and…

Computation and Language · Computer Science 2025-08-27 Yijiong Yu

Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM) inference by using a Small Speculative Model (SSM) to generate candidate tokens in a so-called speculation phase, which are subsequently…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-21 Fahao Chen , Peng Li , Tom H. Luan , Zhou Su , Jing Deng

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Computer Vision and Pattern Recognition · Computer Science 2022-02-22 Gregor Geigle , Jonas Pfeiffer , Nils Reimers , Ivan Vulić , Iryna Gurevych

Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to…

Hardware Architecture · Computer Science 2025-10-22 Yushu Zhao , Yubin Qin , Yang Wang , Xiaolong Yang , Huiming Han , Shaojun Wei , Yang Hu , Shouyi Yin

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…

Computation and Language · Computer Science 2021-01-25 Orion Weller , Matthias Sperber , Christian Gollan , Joris Kluivers

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a…

Computation and Language · Computer Science 2024-12-17 Yunfei Cheng , Aonan Zhang , Xuanyu Zhang , Chong Wang , Yi Wang

Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-29 Talor Abramovich , Maor Ashkenazi , Izzy Putterman , Benjamin Chislett , Tiyasa Mitra , Bita Darvish Rouhani , Ran Zilberstein , Yonatan Geifman

The recommendation system, relying on historical observational data to model the complex relationships among the users and items, has achieved great success in real-world applications. Selection bias is one of the most important issues of…

Machine Learning · Computer Science 2022-01-14 Ruichu Cai , Fengzhu Wu , Zijian Li , Jie Qiao , Wei Chen , Yuexing Hao , Hao Gu

Direct speech translation (ST) models often struggle with rare words. Incorrect translation of these words can have severe consequences, impacting translation quality and user trust. While rare word translation is inherently challenging for…

Computation and Language · Computer Science 2024-10-02 Siqi Li , Danni Liu , Jan Niehues

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Computation and Language · Computer Science 2025-12-18 Chendong Sun , Ali Mao , Lei Xu , mingmin Chen

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…

Computation and Language · Computer Science 2024-10-22 Esteban Garces Arias , Julian Rodemann , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, these methods suffer…

Computation and Language · Computer Science 2025-05-27 Zhihai Wang , Jie Wang , Jilai Pan , Xilin Xia , Huiling Zhen , Mingxuan Yuan , Jianye Hao , Feng Wu

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer…

Artificial Intelligence · Computer Science 2025-09-09 Sining Zhoubian , Dan Zhang , Jie Tang

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…

Computation and Language · Computer Science 2026-02-05 Zihan Lin , Xiaohan Wang , Jie Cao , Jiajun Chai , Guojun Yin , Wei Lin , Ran He