English
Related papers

Related papers: Multi-Token Prediction via Self-Distillation

200 papers

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Computation and Language · Computer Science 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the…

Computation and Language · Computer Science 2025-02-06 Andrea Santilli , Silvio Severino , Emilian Postolache , Valentino Maiorca , Michele Mancusi , Riccardo Marin , Emanuele Rodolà

Small Language Models (SLMs, under 10B parameters) are attractive for private, on-device deployment, yet they frequently fail on strict constraint-satisfaction problems due to linear, overconfident reasoning traces that do not recover from…

Computation and Language · Computer Science 2026-01-22 Aradhya Dixit , Tianxi Liang , Jai Telang

Masked Diffusion Models (MDMs) offer a promising alternative to autoregressive language models by enabling parallel token generation and bidirectional context modeling. However, their inference speed is significantly limited by the…

Machine Learning · Computer Science 2026-04-08 Satyam Goyal , Kushal Patel , Tanush Mittal , Arjun Laxman

Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (GenAI), owing to their remarkable performance in tasks such as text-to-image synthesis. However, practical DMs, such as stable diffusion,…

Machine Learning · Computer Science 2025-08-18 Xuhui Fan , Zhangkai Wu , Hongyu Wu

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Machine Learning · Computer Science 2025-09-24 Yuxuan Cai , Xiaozhuan Liang , Xinghua Wang , Jin Ma , Haijin Liang , Jinwen Luo , Xinyu Zuo , Lisheng Duan , Yuyang Yin , Xi Chen

We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…

Computation and Language · Computer Science 2023-12-13 Ibtihel Amara , Vinija Jain , Aman Chadha

Code retrieval aims to provide users with desired code snippets based on users' natural language queries. With the development of deep learning technologies, adopting pre-trained models for this task has become mainstream. Considering the…

Software Engineering · Computer Science 2025-08-04 Wenchao Gu , Zongyi Lyu , Yanlin Wang , Hongyu Zhang , Cuiyun Gao , Michael R. Lyu

This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research interest in recent years. SD is introduced as an innovative…

Computation and Language · Computer Science 2025-03-04 Heming Xia , Cunxiao Du , Yongqi Li , Qian Liu , Wenjie Li

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…

Computation and Language · Computer Science 2022-10-03 Charlie Snell , Dan Klein , Ruiqi Zhong

Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach this problem from a data-centric perspective, finding that…

Computation and Language · Computer Science 2026-02-19 Jiaming Fan , Daming Cao , Xiangzhong Luo , Jiale Fu , Chonghan Liu , Xu Yang

Speculative decoding stands as a pivotal technique to expedite inference in autoregressive (large) language models. This method employs a smaller draft model to speculate a block of tokens, which the target model then evaluates for…

Computation and Language · Computer Science 2024-10-15 Siru Ouyang , Shuohang Wang , Minhao Jiang , Ming Zhong , Donghan Yu , Jiawei Han , Yelong Shen

Reasoning distillation has emerged as a prevailing paradigm for transferring reasoning capabilities from large reasoning models to small language models. Yet, reasoning distillation risks data contamination: benchmark data may inadvertently…

Computation and Language · Computer Science 2026-05-11 Hengxiang Zhang , Hyeong Kyu Choi , Sharon Li , Hongxin Wei

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Computation and Language · Computer Science 2026-02-17 Miles Williams , Young D. Kwon , Rui Li , Alexandros Kouris , Stylianos I. Venieris

While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer have made their behavior somewhat opaque. To mitigate this…

Computation and Language · Computer Science 2023-06-06 Byung-Doh Oh , William Schuler

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

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts…

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

The slow, sequential nature of autoregressive (AR) language models has driven the adoption of parallel decoding methods. However, these non-AR models often sacrifice generation quality as they struggle to model the complex joint…

Computation and Language · Computer Science 2026-03-24 Chi Zhang , Xixi Hu , Bo Liu , Qiang Liu

Recent advances in fast sampling methods for diffusion models have demonstrated significant potential to accelerate generation on image modalities. We apply these methods to 3-dimensional molecular conformations by building on the recently…

Quantitative Methods · Quantitative Biology 2024-04-23 Romain Lacombe , Neal Vaidya
‹ Prev 1 4 5 6 7 8 10 Next ›