English
Related papers

Related papers: Multi-Token Residual Prediction

200 papers

Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by the trade-off between draft quality and drafting cost:…

Computation and Language · Computer Science 2026-05-29 Jianuo Huang , Yaojie Zhang , Qituan Zhang , Hao Lin , Hanlin Xu , Linfeng Zhang

Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read"…

Computation and Language · Computer Science 2023-01-24 Omar Khattab , Keshav Santhanam , Xiang Lisa Li , David Hall , Percy Liang , Christopher Potts , Matei Zaharia

A recent study showed that large language models (LLMs) can reconstruct surprisingly long texts - up to thousands of tokens - via autoregressive generation from just one trained input embedding. In this work, we explore whether…

Computation and Language · Computer Science 2025-11-04 Gleb Mezentsev , Ivan Oseledets

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vision-Language Models (DVLMs) are particularly attractive…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Jingqi Xu , Jingxi Lu , Chenghao Li , Sreetama Sarkar , Souvik Kundu , Peter A. Beerel

Large Language Models (LLMs) possess latent multi-token prediction (MTP) abilities despite being trained only for next-token generation. We introduce ESP (Embedding-Space Probing), a simple and training-free MTP method that probes an LLM…

Computation and Language · Computer Science 2026-05-29 Raghavv Goel , Mukul Gagrani , Mingu Lee , Chris Lott

Diffusion language models (DLMs) have strong theoretical efficiency but are limited by fixed-length decoding and incompatibility with key-value (KV) caches. Block diffusion mitigates these issues, yet still enforces a fixed block size and…

Computation and Language · Computer Science 2025-09-30 Yangzhou Liu , Yue Cao , Hao Li , Gen Luo , Zhe Chen , Weiyun Wang , Xiaobo Liang , Biqing Qi , Lijun Wu , Changyao Tian , Yanting Zhang , Yuqiang Li , Tong Lu , Yu Qiao , Jifeng Dai , Wenhai Wang

Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirectional context modeling. However, harnessing this flexibility…

Computation and Language · Computer Science 2026-05-28 Jiyeon Kim , Sungik Choi , Yongrae Jo , Moontae Lee , Minjoon Seo

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Machine Learning · Computer Science 2025-05-27 Yixuan Wang , Yijun Liu , Shiyu ji , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), including byte-level LLMs, which are tokeniser-free but prohibitively slow. However, existing MTP methods often…

We introduce GateSkip, a simple residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs. Each Attention/MLP branch is equipped with a sigmoid-linear gate that condenses the branch's output before it…

Computation and Language · Computer Science 2026-02-10 Filipe Laitenberger , Dawid Kopiczko , Cees G. M. Snoek , Yuki M. Asano

Autoregressive large language models (LLMs) are bottlenecked by sequential decoding, where each new token typically requires executing all transformer layers. Existing dynamic-depth and layer-skipping methods reduce this cost, but often…

Computation and Language · Computer Science 2026-01-07 Hossein Rajabzadeh , Maryam Dialameh , Chul B. Park , Il-Min Kim , Hyock Ju Kwon

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we…

Diffusion language models (DLMs) offer a structural alternative to autoregressive generation: denoising can update tokens in arbitrary orders or in parallel rather than along a fixed left-to-right chain. In practice, fast DLM decoding…

Machine Learning · Computer Science 2026-05-12 Jeonseong Kim

Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often causes substantial quality degradation. We…

Computation and Language · Computer Science 2026-05-19 Fanqin Zeng , Feng Hong , Geng Yu , Huangjie Zheng , Xiaofeng Cao , Ya Zhang , Bo Han , Yanfeng Wang , Jiangchao Yao

Massive parameters of LLMs have made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on additional architectures…

Computation and Language · Computer Science 2025-05-27 Xianzhen Luo , Yixuan Wang , Qingfu Zhu , Zhiming Zhang , Xuanyu Zhang , Qing Yang , Dongliang Xu

Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. We introduce VocalNet-1B and VocalNet-8B, a series of high-performance, low-latency speech LLMs enabled by a scalable and model-agnostic…

Computation and Language · Computer Science 2025-04-23 Yuhao Wang , Heyang Liu , Ziyang Cheng , Ronghua Wu , Qunshan Gu , Yanfeng Wang , Yu Wang

Batch inference workloads for causal transformer models frequently process sequences that share common prefixes, such as system prompts, few-shot examples, or shared queries. Standard inference engines treat each sequence independently,…

Machine Learning · Computer Science 2026-01-22 Michael Feil , Julius Lipp

Masked diffusion language models (MDLMs) have recently emerged as a new paradigm in language modeling, offering flexible generation dynamics and enabling efficient parallel decoding. However, existing decoding strategies for pre-trained…

Computation and Language · Computer Science 2026-03-17 Xueyu Zhou , Yangrong Hu , Jian Huang

Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone…

Machine Learning · Computer Science 2026-04-24 Liming Liu , Binxuan Huang , Zixuan Zhang , Xin Liu , Bing Yin , Tuo Zhao

Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this…

Computation and Language · Computer Science 2026-02-26 Yuetao Chen , Xuliang Wang , Xinzhou Zheng , Ming Li , Peng Wang , Hong Xu