English
Related papers

Related papers: PALBERT: Teaching ALBERT to Ponder

200 papers

Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models. In…

Computation and Language · Computer Science 2020-12-14 Yiming Cui , Wanxiang Che , Ting Liu , Bing Qin , Shijin Wang , Guoping Hu

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Computers and Society · Computer Science 2019-12-03 Benjamin Clavié , Kobi Gal

Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce…

Artificial Intelligence · Computer Science 2025-12-04 Emil Biju , Shayan Talaei , Zhemin Huang , Mohammadreza Pourreza , Azalia Mirhoseini , Amin Saberi

Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length…

Computation and Language · Computer Science 2022-03-29 Xin Huang , Ashish Khetan , Rene Bidart , Zohar Karnin

This paper is aimed at developing a method that reduces the computational cost of convolutional neural networks (CNN) during inference. Conventionally, the input data pass through a fixed neural network architecture. However, easy examples…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Edanur Demir , Emre Akbas

Modern predictive models are often deployed to environments in which computational budgets are dynamic. Anytime algorithms are well-suited to such environments as, at any point during computation, they can output a prediction whose quality…

Machine Learning · Computer Science 2023-10-31 Metod Jazbec , James Urquhart Allingham , Dan Zhang , Eric Nalisnick

BERT-based models are currently used for solving nearly all Natural Language Processing (NLP) tasks and most often achieve state-of-the-art results. Therefore, the NLP community conducts extensive research on understanding these models, but…

Computation and Language · Computer Science 2021-05-06 Robert Mroczkowski , Piotr Rybak , Alina Wróblewska , Ireneusz Gawlik

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Xuting Liu , Daniel Alexander , Siva Kesava Reddy Kakarla , Behnaz Arzani , Vincent Liu

Decision-Focused Learning (DFL) trains predictors to improve downstream decision quality, but computing regret gradients typically requires differentiating through solvers or relying on surrogate losses, which can be computationally…

Machine Learning · Computer Science 2026-05-20 Junhyeong Lee , Sangjin Jin , Yongjae Lee

Lack of training data in low-resource languages presents huge challenges to sequence labeling tasks such as named entity recognition (NER) and machine reading comprehension (MRC). One major obstacle is the errors on the boundary of…

Computation and Language · Computer Science 2020-11-12 Shining Liang , Linjun Shou , Jian Pei , Ming Gong , Wanli Zuo , Daxin Jiang

Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers,…

Machine Learning · Computer Science 2026-02-05 Yanhua Zhao

Agents powered by large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments. However, such agents often suffer from inefficiencies in multi-turn interactions, frequently…

Computation and Language · Computer Science 2025-09-23 Qingyu Lu , Liang Ding , Siyi Cao , Xuebo Liu , Kanjian Zhang , Jinxia Zhang , Dacheng Tao

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Information Retrieval · Computer Science 2020-02-18 Wenhao Lu , Jian Jiao , Ruofei Zhang

Recent advances in Transformer-based large language models (LLMs) have led to significant performance improvements across many tasks. These gains come with a drastic increase in the models' size, potentially leading to slow and costly use…

Computation and Language · Computer Science 2022-10-26 Tal Schuster , Adam Fisch , Jai Gupta , Mostafa Dehghani , Dara Bahri , Vinh Q. Tran , Yi Tay , Donald Metzler

Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate…

Machine Learning · Computer Science 2026-05-13 Zizhao Chen , Yuying Li , Siting Lin , Lianxi Wang

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…

Computation and Language · Computer Science 2024-06-27 Richard Yuanzhe Pang , Weizhe Yuan , Kyunghyun Cho , He He , Sainbayar Sukhbaatar , Jason Weston

We propose a neural network architecture, called TransNet, that combines planning and model learning for solving Partially Observable Markov Decision Processes (POMDPs) with non-uniform system dynamics. The past decade has seen a…

Robotics · Computer Science 2019-07-11 Nicholas Collins , Hanna Kurniawati

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Computation and Language · Computer Science 2023-02-23 Mohammad Akbar-Tajari , Sara Rajaee , Mohammad Taher Pilehvar

Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can…

Computation and Language · Computer Science 2023-05-10 Jiayi Tian , Chao Fang , Haonan Wang , Zhongfeng Wang

Transformer-based deep NLP models are trained using hundreds of millions of parameters, limiting their applicability in computationally constrained environments. In this paper, we study the cause of these limitations by defining a notion of…

Computation and Language · Computer Science 2020-10-07 Fahim Dalvi , Hassan Sajjad , Nadir Durrani , Yonatan Belinkov