English
Related papers

Related papers: Direct Multi-Token Decoding

200 papers

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of factual knowledge. However, understanding their underlying reasoning and internal mechanisms in exploiting this knowledge remains a key research area.…

Computation and Language · Computer Science 2024-08-07 Marco Bronzini , Carlo Nicolini , Bruno Lepri , Jacopo Staiano , Andrea Passerini

Vision Large Language Models (VLLMs) usually take input as a concatenation of image token embeddings and text token embeddings and conduct causal modeling. However, their internal behaviors remain underexplored, raising the question of…

Computation and Language · Computer Science 2025-05-16 Houjing Wei , Yuting Shi , Naoya Inoue

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding. However, extending these models to fine-grained dense prediction tasks, such as semantic segmentation and depth…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Yi Li , Hongze Shen , Lexiang Tang , Xin Li , Xinpeng Ding , Yinsong Liu , Deqiang Jiang , Xing Sun , Xiaomeng Li

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…

Computation and Language · Computer Science 2026-03-26 Rui Wei , Rui Du , Hanfei Yu , Devesh Tiwari , Jian Li , Zhaozhuo Xu , Hao Wang

Currently, Large Language Models (LLMs) have achieved remarkable results in machine translation. However, their performance in multi-domain translation (MDT) is less satisfactory, the meanings of words can vary across different domains,…

Computation and Language · Computer Science 2026-03-17 Zhibo Man , Yuanmeng Chen , Yujie Zhang , Jinan Xu

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Computation and Language · Computer Science 2025-02-11 Jun Zhang , Jue Wang , Huan Li , Lidan Shou , Ke Chen , Gang Chen , Sharad Mehrotra

Previous multi-task dense prediction studies developed complex pipelines such as multi-modal distillations in multiple stages or searching for task relational contexts for each task. The core insight beyond these methods is to maximize the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Yangyang Xu , Xiangtai Li , Haobo Yuan , Yibo Yang , Lefei Zhang

While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unidirectional and bidirectional models are typically trained…

Computation and Language · Computer Science 2025-02-17 Savya Khosla , Aditi Tiwari , Kushal Kafle , Simon Jenni , Handong Zhao , John Collomosse , Jing Shi

Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their parameters and gradients,…

Computation and Language · Computer Science 2025-06-03 Zifeng Cheng , Zhaoling Chen , Zhiwei Jiang , Yafeng Yin , Cong Wang , Shiping Ge , Qing Gu

Deep learning methods have predominantly been applied to large artificial neural networks. Despite their state-of-the-art performance, these large networks typically do not generalize well to datasets with limited sample sizes. In this…

Machine Learning · Statistics 2016-11-17 Eric Strobl , Shyam Visweswaran

Techniques enabling large language models (LLMs) to "think more" by generating and attending to intermediate reasoning steps have shown promise in solving complex problems. However, the standard approaches generate sequences of discrete…

Computation and Language · Computer Science 2024-12-24 Luyang Liu , Jonas Pfeiffer , Jiaxing Wu , Jun Xie , Arthur Szlam

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

Large language models (LLMs) provide strong semantic priors that can improve multi-talker automatic speech recognition (MT-ASR), but using an LLM as an autoregressive decoder is computationally expensive and remains fragile under heavy…

Sound · Computer Science 2026-03-12 Hao Shi , Yusuke Fujita , Roman Koshkin , Mengjie Zhao , Yuan Gao , Lianbo Liu , Yui Sudo

Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the…

Computation and Language · Computer Science 2024-09-24 Xinglin Lyu , Junhui Li , Yanqing Zhao , Min Zhang , Daimeng Wei , Shimin Tao , Hao Yang , Min Zhang

Although reward models have been successful in improving multimodal large language models, the reward models themselves remain brutal and contain minimal information. Notably, existing reward models only mimic human annotations by assigning…

Machine Learning · Computer Science 2025-02-26 Deqing Fu , Tong Xiao , Rui Wang , Wang Zhu , Pengchuan Zhang , Guan Pang , Robin Jia , Lawrence Chen

Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce…

Machine Learning · Computer Science 2026-02-03 Fengrui Zuo , Zhiwei Ke , Yiming Liu , Wenqi Lou , Chao Wang , Xuehai Zhou

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…

Computation and Language · Computer Science 2025-05-30 Milan Gritta , Huiyin Xue , Gerasimos Lampouras

Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in…

Machine Learning · Computer Science 2026-04-21 Qimin Zhong , Hao Liao , Haiming Qin , Mingyang Zhou , Rui Mao , Wei Chen , Naipeng Chao