English
Related papers

Related papers: Fast and Robust Early-Exiting Framework for Autore…

200 papers

Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks, yet their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and…

Machine Learning · Computer Science 2025-11-07 Mingyu Sung , Vikas Palakonda , Suhwan Im , Sunghwan Moon , Il-Min Kim , Sangseok Yun , Jae-Mo Kang

Recent advances in large language models (LLMs) have accelerated progress toward artificial general intelligence, with inference-time scaling emerging as a key technique. Contemporary approaches leverage either sequential reasoning…

Computation and Language · Computer Science 2025-07-10 Zenan Xu , Zexuan Qiu , Guanhua Huang , Kun Li , Siheng Li , Chenchen Zhang , Kejiao Li , Qi Yi , Yuhao Jiang , Bo Zhou , Fengzong Lian , Zhanhui Kang

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase…

Computation and Language · Computer Science 2021-09-10 Tal Schuster , Adam Fisch , Tommi Jaakkola , Regina Barzilay

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

Computation and Language · Computer Science 2021-05-31 Tianxiang Sun , Yunhua Zhou , Xiangyang Liu , Xinyu Zhang , Hao Jiang , Zhao Cao , Xuanjing Huang , Xipeng Qiu

Deep neural networks have become larger over the years with increasing demand of computational resources for inference; incurring exacerbate costs and leaving little room for deployment on devices with limited battery and other resources…

Machine Learning · Computer Science 2021-09-28 Aaqib Saeed

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Computation and Language · Computer Science 2026-01-29 Zhimin Qiu , Di Wu , Feng Liu , Yuxiao Wang

The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative and parallel decoding techniques attempt to mitigate this, they face…

Artificial Intelligence · Computer Science 2024-10-22 Aishwarya P S , Pranav Ajit Nair , Yashas Samaga , Toby Boyd , Sanjiv Kumar , Prateek Jain , Praneeth Netrapalli

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

Artificial Intelligence · Computer Science 2025-12-23 Qinglin Zeng , Jing Yang , Keze Wang

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

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in…

Computation and Language · Computer Science 2018-11-13 Jindřich Libovický , Jindřich Helcl

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Computation and Language · Computer Science 2025-10-06 Wenrui Bao , Zhiben Chen , Dan Xu , Yuzhang Shang

Diffusion language models offer parallel token generation and inherent bidirectionality, promising more efficient and powerful sequence modeling compared to autoregressive approaches. However, state-of-the-art diffusion models (e.g., Dream…

Computation and Language · Computer Science 2025-10-10 Zhanqiu Hu , Jian Meng , Yash Akhauri , Mohamed S. Abdelfattah , Jae-sun Seo , Zhiru Zhang , Udit Gupta

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a…

Computation and Language · Computer Science 2025-10-27 Yeongbin Seo , Dongha Lee , Jaehyung Kim , Jinyoung Yeo

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xinwan Wen , Bowen Li , Jiajun Luo , Ye Li , Zhi Wang

Deep Ensembles are a simple, reliable, and effective method of improving both the predictive performance and uncertainty estimates of deep learning approaches. However, they are widely criticised as being computationally expensive, due to…

Machine Learning · Computer Science 2023-10-10 Guoxuan Xia , Christos-Savvas Bouganis

Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approaches typically rely on single-model confidence thresholds,…

Machine Learning · Computer Science 2026-02-02 Matteo Gambella , Fabrizio Pittorino , Giuliano Casale , Manuel Roveri

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations…

Machine Learning · Computer Science 2026-03-10 Deng Pan , Nuno Moniz , Nitesh Chawla

Personalized Federated Learning (PFL) enables collaboratively model training on decentralized, heterogeneous data while tailoring them to each client's unique distribution. However, existing PFL methods produce static models with a fixed…

Machine Learning · Computer Science 2026-01-16 Boyi Liu , Zimu Zhou , Yongxin Tong

Reliable evaluation of large language models is essential to ensure their applicability in practical scenarios. Traditional benchmark-based evaluation methods often rely on fixed reference answers, limiting their ability to capture…

Computation and Language · Computer Science 2025-10-02 Sujeong Lee , Hayoung Lee , Seongsoo Heo , Wonik Choi

Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications. However, they are also notorious for being slow in inference, which makes them difficult to deploy in real-time applications. We…

Computation and Language · Computer Science 2020-04-28 Ji Xin , Raphael Tang , Jaejun Lee , Yaoliang Yu , Jimmy Lin