English
Related papers

Related papers: RigLSTM: Recurrent Independent Grid LSTM for Gener…

200 papers

Progress in reinforcement learning (RL) research is often driven by the design of new, challenging environments -- a costly undertaking requiring skills orthogonal to that of a typical machine learning researcher. The complexity of…

Artificial Intelligence · Computer Science 2022-10-14 Christopher Bamford , Minqi Jiang , Mikayel Samvelyan , Tim Rocktäschel

Modularity is a compelling solution to continual learning (CL), the problem of modeling sequences of related tasks. Learning and then composing modules to solve different tasks provides an abstraction to address the principal challenges of…

Machine Learning · Computer Science 2021-11-16 Oleksiy Ostapenko , Pau Rodriguez , Massimo Caccia , Laurent Charlin

Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it…

Artificial Intelligence · Computer Science 2026-01-28 Andrew Jaffe , Noah Reicin , Jinho D. Choi

Inference-time scaling has attracted much attention which significantly enhance the performance of Large Language Models (LLMs) in complex reasoning tasks by increasing the length of Chain-of-Thought. These longer intermediate reasoning…

Computation and Language · Computer Science 2025-05-21 Hongru Wang , Deng Cai , Wanjun Zhong , Shijue Huang , Jeff Z. Pan , Zeming Liu , Kam-Fai Wong

Recurrent neural networks (RNNs) have been widely used for processing sequential data. However, RNNs are commonly difficult to train due to the well-known gradient vanishing and exploding problems and hard to learn long-term patterns. Long…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Shuai Li , Wanqing Li , Chris Cook , Ce Zhu , Yanbo Gao

Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the…

Machine Learning · Computer Science 2017-02-28 Zhiyuan Tang , Ying Shi , Dong Wang , Yang Feng , Shiyue Zhang

We introduce MinConvLSTM and MinConvGRU, two novel spatiotemporal models that combine the spatial inductive biases of convolutional recurrent networks with the training efficiency of minimal, parallelizable RNNs. Our approach extends the…

Machine Learning · Computer Science 2025-08-06 Coşku Can Horuz , Sebastian Otte , Martin V. Butz , Matthias Karlbauer

Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms. Liquid State Machine (LSM) is a bio-inspired RC model that mimics the cortical microcircuits and uses spiking neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-05-21 Dipayan Das , Saumik Bhattacharya , Umapada Pal , Sukalpa Chanda

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

Machine Learning · Computer Science 2019-12-04 Jeremy Gordon , David Rawlinson , Subutai Ahmad

Incremental learning is a machine learning approach that involves training a model on a sequence of tasks, rather than all tasks at once. This ability to learn incrementally from a stream of tasks is crucial for many real-world…

Machine Learning · Computer Science 2024-02-21 Junwei Su , Difan Zou , Zijun Zhang , Chuan Wu

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…

Machine Learning · Computer Science 2021-03-25 Andrea Cossu , Antonio Carta , Davide Bacciu

Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed…

Information Retrieval · Computer Science 2025-03-26 Yuan Li , Jun Hu , Jiaxin Jiang , Zemin Liu , Bryan Hooi , Bingsheng He

Recurrent Neural Networks (RNNs) have been shown to capture various aspects of syntax from raw linguistic input. In most previous experiments, however, learning happens over unrealistic corpora, which do not reflect the type and amount of…

Computation and Language · Computer Science 2024-11-12 Ludovica Pannitto , Aurélie Herbelot

In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting. The principal target of our approach is the automatic…

Machine Learning · Computer Science 2021-01-19 Ammar Shaker , Shujian Yu , Francesco Alesiani

In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer…

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions. Despite the existence of a large…

Machine Learning · Computer Science 2025-02-28 Shangding Gu , Laixi Shi , Muning Wen , Ming Jin , Eric Mazumdar , Yuejie Chi , Adam Wierman , Costas Spanos

Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have been successfully applied to a variety of sequence modeling tasks. In this paper we develop Tree Long Short-Term Memory…

Computation and Language · Computer Science 2016-04-05 Xingxing Zhang , Liang Lu , Mirella Lapata

Large language models (LLMs) have demonstrated remarkable capabilities across various domains, yet their application to relational deep learning (RDL) remains underexplored. Existing approaches adapt LLMs by traversing relational links…

Computation and Language · Computer Science 2025-06-09 Fang Wu , Vijay Prakash Dwivedi , Jure Leskovec

This paper explores the use of Large Language Models (LLMs) for sequential recommendation, which predicts users' future interactions based on their past behavior. We introduce a new concept, "Integrating Recommendation Systems as a New…

Information Retrieval · Computer Science 2024-12-24 Kai Zheng , Qingfeng Sun , Can Xu , Peng Yu , Qingwei Guo

This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be…

Machine Learning · Computer Science 2023-06-23 Gyuhak Kim , Changnan Xiao , Tatsuya Konishi , Bing Liu