English
Related papers

Related papers: DynaMo: Accelerating Language Model Inference with…

200 papers

Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an…

Computation and Language · Computer Science 2026-04-09 Ziqi Jin , Lei Wang , Ziwei Luo , Aixin Sun

Standard autoregressive language models generate text by repeatedly selecting a discrete next token, coupling prediction with irreversible commitment at every step. We show that token selection is not the only viable autoregressive…

Computation and Language · Computer Science 2026-04-07 Oshri Naparstek

Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models. Particularly, auto-regressive language models generate texts token by…

Computation and Language · Computer Science 2026-02-19 Daiki Chijiwa , Taku Hasegawa , Kyosuke Nishida , Shin'ya Yamaguchi , Tomoya Ohba , Tamao Sakao , Susumu Takeuchi

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…

Computation and Language · Computer Science 2023-06-14 Yuchen Zhuang , Yue Yu , Lingkai Kong , Xiang Chen , Chao Zhang

The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference…

Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address this limitation, we…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Minglei Shi , Ziyang Yuan , Haotian Yang , Xintao Wang , Mingwu Zheng , Xin Tao , Wenliang Zhao , Wenzhao Zheng , Jie Zhou , Jiwen Lu , Pengfei Wan , Di Zhang , Kun Gai

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2024-05-01 Fabian Gloeckle , Badr Youbi Idrissi , Baptiste Rozière , David Lopez-Paz , Gabriel Synnaeve

Modern autoregressive speech synthesis models leveraging language models have demonstrated remarkable performance. However, the sequential nature of next token prediction in these models leads to significant latency, hindering their…

Sound · Computer Science 2025-06-04 Zijian Lin , Yang Zhang , Yougen Yuan , Yuming Yan , Jinjiang Liu , Zhiyong Wu , Pengfei Hu , Qun Yu

State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in…

Computation and Language · Computer Science 2020-07-01 Jungo Kasai , James Cross , Marjan Ghazvininejad , Jiatao Gu

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models)…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Zhengdao Li , Siheng Wang , Zeyu Zhang , Hao Tang

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite these advantages, MDMs face a fundamental limitation: once…

Machine Learning · Computer Science 2026-03-06 Yair Schiff , Omer Belhasin , Roy Uziel , Guanghan Wang , Marianne Arriola , Gilad Turok , Michael Elad , Volodymyr Kuleshov

Prior masked modeling motion generation methods predominantly study text-to-motion. We present DiMo, a discrete diffusion-style framework, which extends masked modeling to bidirectional text--motion understanding and generation. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Ning Zhang , Zhengyu Li , Kwong Weng Loh , Mingxi Xu , Qi Wang , Zhengyu Wen , Xiaoyu He , Wei Zhao , Kehong Gong , Mingyuan Zhang

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is…

Computation and Language · Computer Science 2026-02-04 Jinbin Zhang , Nasib Ullah , Erik Schultheis , Rohit Babbar

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

Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…

Computation and Language · Computer Science 2024-06-04 Wenhong Zhu , Hongkun Hao , Zhiwei He , Yiming Ai , Rui Wang

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions…

Machine Learning · Computer Science 2025-10-27 Myunsoo Kim , Donghyeon Ki , Seong-Woong Shim , Byung-Jun Lee

Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models since multiple tokens can be sampled in parallel during each…

Machine Learning · Computer Science 2025-06-10 Guhao Feng , Yihan Geng , Jian Guan , Wei Wu , Liwei Wang , Di He

The prevalence of Transformer-based pre-trained language models (PLMs) has led to their wide adoption for various natural language processing tasks. However, their excessive overhead leads to large latency and computational costs. The…

Computation and Language · Computer Science 2023-05-23 Wenxi Tan

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

Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words' local context, a natural way to induce context-dependent representations is to perform…

Machine Learning · Statistics 2015-06-02 David Belanger , Sham Kakade