English
Related papers

Related papers: Multi-Token Prediction via Self-Distillation

200 papers

Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…

Computation and Language · Computer Science 2024-10-10 Zilin Xiao , Hongming Zhang , Tao Ge , Siru Ouyang , Vicente Ordonez , Dong Yu

Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…

Computation and Language · Computer Science 2026-03-06 Felix Draxler , Justus Will , Farrin Marouf Sofian , Theofanis Karaletsos , Sameer Singh , Stephan Mandt

Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…

Computation and Language · Computer Science 2024-01-15 Sen Yang , Shujian Huang , Xinyu Dai , Jiajun Chen

Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Seanie Lee , Minki Kang , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computation and Language · Computer Science 2025-10-27 Benjamin Minixhofer , Ivan Vulić , Edoardo Maria Ponti

Automated machine learning (AutoML) can produce complex model ensembles by stacking, bagging, and boosting many individual models like trees, deep networks, and nearest neighbor estimators. While highly accurate, the resulting predictors…

Machine Learning · Computer Science 2021-11-05 Rasool Fakoor , Jonas Mueller , Nick Erickson , Pratik Chaudhari , Alexander J. Smola

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

Computation and Language · Computer Science 2026-01-06 Zishun Yu , Shangzhe Li , Xinhua Zhang

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

Sequential recommendation models user interests based on historical behaviors to provide personalized recommendation. Previous sequential recommendation algorithms primarily employ neural networks to extract features of user interests,…

Information Retrieval · Computer Science 2024-09-24 Li Li , Mingyue Cheng , Zhiding Liu , Hao Zhang , Qi Liu , Enhong Chen

We propose a novel speculative decoding method tailored for multi-sample reasoning scenarios, such as self-consistency and Best-of-N sampling. Our method exploits the intrinsic consensus of parallel generation paths to synthesize…

Computation and Language · Computer Science 2025-03-10 Yiwei Li , Jiayi Shi , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Yueqi Zhang , Ji Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

We introduce Transfusion, a recipe for training a multi-modal model over discrete and continuous data. Transfusion combines the language modeling loss function (next token prediction) with diffusion to train a single transformer over…

Artificial Intelligence · Computer Science 2024-08-21 Chunting Zhou , Lili Yu , Arun Babu , Kushal Tirumala , Michihiro Yasunaga , Leonid Shamis , Jacob Kahn , Xuezhe Ma , Luke Zettlemoyer , Omer Levy

Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these…

Computation and Language · Computer Science 2025-10-23 Yuezhou Hu , Jiaxin Guo , Xinyu Feng , Tuo Zhao

Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and…

Information Retrieval · Computer Science 2023-06-19 Sean MacAvaney , Xi Wang

Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion…

Machine Learning · Computer Science 2026-05-25 Jean-Marie Lemercier , Tomas Geffner , Karsten Kreis , Morteza Mardani , Arash Vahdat , Ante Jukić

Diffusion large language models (dLLMs) have recently drawn considerable attention within the research community as a promising alternative to autoregressive generation, offering parallel token prediction and lower inference latency. Yet,…

Computation and Language · Computer Science 2025-10-01 Zigeng Chen , Gongfan Fang , Xinyin Ma , Ruonan Yu , Xinchao Wang

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels. To ground this prediction process in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Kaiyu Yue , Bor-Chun Chen , Jonas Geiping , Hengduo Li , Tom Goldstein , Ser-Nam Lim

Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern…

Machine Learning · Computer Science 2025-08-19 Nikita Gushchin , David Li , Daniil Selikhanovych , Evgeny Burnaev , Dmitry Baranchuk , Alexander Korotin

This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution holds valuable insights for the student, beyond the…

Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…

Computation and Language · Computer Science 2025-11-05 Jameson Sandler , Jacob K. Christopher , Thomas Hartvigsen , Ferdinando Fioretto