English
Related papers

Related papers: Length Generalization with Log-Depth Recurrent Uni…

200 papers

Recurrent neural networks (RNNs) have been drawing much attention with great success in many applications like speech recognition and neural machine translation. Long short-term memory (LSTM) is one of the most popular RNN units in deep…

Computation and Language · Computer Science 2018-12-10 Heeyoul Choi

Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this…

Computation and Language · Computer Science 2017-08-09 Stephen Merity , Nitish Shirish Keskar , Richard Socher

The field of meta-learning has seen a dramatic rise in interest in recent years. In existing meta-learning approaches, learning tasks for training meta-models are usually collected from public datasets, which brings the difficulty of…

Machine Learning · Computer Science 2021-11-23 Zhaoyang Hai , Xiabi Liu , Yuchen Ren , Nouman Q. Soomro

Multimodal Large Language Models (MLLMs), particularly smaller, deployable variants, exhibit a critical deficiency in understanding temporal and procedural visual data, a bottleneck hindering their application in real-world embodied AI.…

Artificial Intelligence · Computer Science 2026-02-24 Zhenkun Gao , Xuhong Wang , Xin Tan , Yuan Xie

Lip-reading has attracted a lot of research attention lately thanks to advances in deep learning. The current state-of-the-art model for recognition of isolated words in-the-wild consists of a residual network and Bidirectional Gated…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Brais Martinez , Pingchuan Ma , Stavros Petridis , Maja Pantic

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors…

Computer Vision and Pattern Recognition · Computer Science 2021-02-09 Yonghyun Kim , Wonpyo Park

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang

Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting remains, where models fail to retain their ability to perform…

Machine Learning · Computer Science 2025-02-21 Karolina Bogacka , Maximilian Höfler , Maria Ganzha , Wojciech Samek , Katarzyna Wasielewska-Michniewska

Understanding spoken language is a highly complex problem, which can be decomposed into several simpler tasks. In this paper, we focus on Spoken Language Understanding (SLU), the module of spoken dialog systems responsible for extracting a…

Computation and Language · Computer Science 2017-06-22 Marco Dinarelli , Yoann Dupont , Isabelle Tellier

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Computation and Language · Computer Science 2025-02-06 Rhea Sanjay Sukthanker , Benedikt Staffler , Frank Hutter , Aaron Klein

In this paper we propose a sequential learning framework for Domain Generalization (DG), the problem of training a model that is robust to domain shift by design. Various DG approaches have been proposed with different motivating…

Computer Vision and Pattern Recognition · Computer Science 2020-04-06 Da Li , Yongxin Yang , Yi-Zhe Song , Timothy Hospedales

Loop transformations are semantics-preserving optimization techniques, widely used to maximize objectives such as parallelism. Despite decades of research, applying the optimal composition of loop transformations remains challenging due to…

Programming Languages · Computer Science 2025-12-19 Yijie Zhi , Yayu Cao , Jianhua Dai , Xiaoyang Han , Jingwen Pu , Qingran Wu , Sheng Cheng , Ming Cai

Self-attention is often viewed as probabilistic query-key lookup, motivating designs that preserve normalized attention scores and fixed positional semantics. We advocate a simpler and more unified perspective: an autoregressive attention…

Machine Learning · Computer Science 2026-02-16 Jiecheng Lu , Shihao Yang

As the applications of large language models (LLMs) expand across diverse fields, the ability of these models to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods, relying on static…

Machine Learning · Computer Science 2024-06-11 Junhao Zheng , Shengjie Qiu , Chengming Shi , Qianli Ma

This study investigates the learnability of Recurrent Neural Networks (RNNs) in classifying structured formal languages, focusing on counter and Dyck languages. Traditionally, both first-order (LSTM) and second-order (O2RNN) RNNs have been…

Computation and Language · Computer Science 2024-10-07 Neisarg Dave , Daniel Kifer , Lee Giles , Ankur Mali

We study length generalization in sequence models on a composite problem involving both state tracking and associative recall. Prior work finds that recurrent networks handle state tracking well but struggle with recall, whereas…

Machine Learning · Computer Science 2025-10-02 Buu Phan , Reza Ebrahimi , Sanjay Haresh , Roland Memisevic

Recently, large language models (LLMs) have demonstrated impressive capabilities in dealing with new tasks with the help of in-context learning (ICL). In the study of Large Vision-Language Models (LVLMs), when implementing ICL, researchers…

Computation and Language · Computer Science 2024-12-11 Ellen Yi-Ge , Jiechao Gao , Wei Han , Wei Zhu

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most…

Machine Learning · Computer Science 2026-05-20 Fei Liu , Rui Zhang , Xi Lin , Zhichao Lu , Qingfu Zhang

Recurrent Neural Networks (RNNs) are widely used in the field of natural language processing (NLP), ranging from text categorization to question answering and machine translation. However, RNNs generally read the whole text from beginning…

Computation and Language · Computer Science 2019-05-29 Ting Huang , Gehui Shen , Zhi-Hong Deng

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…