English
Related papers

Related papers: RecycleGPT: An Autoregressive Language Model with …

200 papers

Large language models achieve strong machine translation quality but incur high inference cost and latency, posing challenges for simultaneous translation. Re-translation provides a practical solution for off-the-shelf LLMs by repeatedly…

Computation and Language · Computer Science 2026-01-06 Linxiao Zeng , Haoyun Deng , Kangyuan Shu , Shizhen Wang

Large language models pre-trained for code generation can generate high-quality short code but often struggle with generating coherent long code and understanding higher-level or system-level specifications. This issue is also observed in…

Computation and Language · Computer Science 2023-04-18 Swapnil Sharma , Nikita Anand , Kranthi Kiran G.

Current state-of-the-art image captioning models adopt autoregressive decoders, \ie they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. To tackle this issue,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Yuanen Zhou , Yong Zhang , Zhenzhen Hu , Meng Wang

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

Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings…

Computation and Language · Computer Science 2023-02-01 Jon Saad-Falcon , Amanpreet Singh , Luca Soldaini , Mike D'Arcy , Arman Cohan , Doug Downey

In this paper, we lay out a vision for analysing semantic trajectory traces and generating synthetic semantic trajectory data (SSTs) using generative language model. Leveraging the advancements in deep learning, as evident by progress in…

Computation and Language · Computer Science 2023-06-27 Shreya Ghosh , Saptarshi Sengupta , Prasenjit Mitra

We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-28 Myeonghun Jeong , Minchan Kim , Joun Yeop Lee , Nam Soo Kim

Large Language Models (LLMs) can exhibit considerable variation in the quality of their sampled outputs. Reranking and selecting the best generation from the sampled set is a popular way of obtaining strong gains in generation quality. In…

Artificial Intelligence · Computer Science 2024-01-15 Siddhartha Jain , Xiaofei Ma , Anoop Deoras , Bing Xiang

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Sound · Computer Science 2018-11-07 Santiago Pascual , Antonio Bonafonte , Joan Serrà

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding…

Information Retrieval · Computer Science 2025-02-27 Xinyu Lin , Chaoqun Yang , Wenjie Wang , Yongqi Li , Cunxiao Du , Fuli Feng , See-Kiong Ng , Tat-Seng Chua

An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models. To further improve model adaptation to…

Computation and Language · Computer Science 2023-11-15 Nohil Park , Joonsuk Park , Kang Min Yoo , Sungroh Yoon

Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…

Computation and Language · Computer Science 2026-05-27 Zhiyang Chen , Daliang Xu , Yinyuan Zhang , Chenghua Wang , Mengwei Xu , Yun Ma

Existing approaches to neural machine translation condition each output word on previously generated outputs. We introduce a model that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude…

Computation and Language · Computer Science 2018-03-12 Jiatao Gu , James Bradbury , Caiming Xiong , Victor O. K. Li , Richard Socher

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

Software Engineering · Computer Science 2024-01-09 Yue Liu , Chakkrit Tantithamthavorn , Yonghui Liu , Li Li

To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic…

Computation and Language · Computer Science 2020-06-30 Dandan Guo , Bo Chen , Ruiying Lu , Mingyuan Zhou

Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…

Computation and Language · Computer Science 2025-09-30 Maxim Divilkovskiy , Vitaly Malygin , Sergey Zlobin , Stanislav Ilyushin , Sultan Isali , Vasily Kalugin , Nuriza Aitassova , Fei Yi , Weidi Zeng

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably…

Computation and Language · Computer Science 2020-06-11 Qiu Ran , Yankai Lin , Peng Li , Jie Zhou

Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequence, which is then validated by the LLM. The effectiveness…

Computation and Language · Computer Science 2024-07-24 Zhuocheng Gong , Jiahao Liu , Ziyue Wang , Pengfei Wu , Jingang Wang , Xunliang Cai , Dongyan Zhao , Rui Yan

Biological machine learning is often bottlenecked by a lack of scaled data. One promising route to relieving data bottlenecks is through high throughput screens, which can experimentally test the activity of $10^6-10^{12}$ protein sequences…

Machine Learning · Statistics 2025-10-21 Eli N. Weinstein , Andrei Slabodkin , Mattia G. Gollub , Elizabeth B. Wood

Embodied Chain-of-Thought (ECoT) reasoning enhances vision-language-action (VLA) models by improving performance and interpretability through intermediate reasoning steps. However, its sequential autoregressive token generation introduces…

Robotics · Computer Science 2025-09-23 Zhekai Duan , Yuan Zhang , Shikai Geng , Gaowen Liu , Joschka Boedecker , Chris Xiaoxuan Lu
‹ Prev 1 8 9 10 Next ›