Related papers: Ken Utilization Layer: Hebbian Replay Within a Stu…

Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly advanced network architectures. However, existing layer attention methods suffer from redundancy,…

High-dimensional reinforcement learning(RL) faces challenges with complex calculations and low sample efficiency in large state-action spaces. Q-learning algorithms struggle particularly with the curse of dimensionality, where the number of…

Designing generalizable agents capable of adapting to diverse embodiments has achieved significant attention in Reinforcement Learning (RL), which is critical for deploying RL agents in various real-world applications. Previous…

Reservoir computing (RC) is an effective method for predicting chaotic systems by using a high-dimensional dynamic reservoir with fixed internal weights, while keeping the learning phase linear, which simplifies training and reduces…

We consider the problem of estimating the remaining useful life (RUL) of a system or a machine from sensor data. Many approaches for RUL estimation based on sensor data make assumptions about how machines degrade. Additionally, sensor data…

Recently, Large Language Models (LLMs) have been widely employed in Conversational Recommender Systems (CRSs). Unlike traditional language model approaches that focus on training, all existing LLMs-based approaches are mainly centered…

Recent advances in Reinforcement Learning with Verified Reward (RLVR) have driven the emergence of more sophisticated cognitive behaviors in large language models (LLMs), thereby enhancing their reasoning capabilities. However, in prior…

Network systems can exhibit memory effects in which the interactions between different pairs of nodes adapt in time, leading to the emergence of preferred connections, patterns, and sub-networks. To a first approximation, this memory can be…

Referring Expression Comprehension (REC), which aims to ground a local visual region via natural language, is a task that heavily relies on multimodal alignment. Most existing methods utilize powerful pre-trained models to transfer…

Deep Convolutional Neural Networks (CNNs) achieve high accuracy but often rely on purely global, gradient-based optimisation, which can lead to overfitting, redundant filters, and reduced interpretability. To address these limitations, we…

Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific…

We present a novel technique called Dynamic Experience Replay (DER) that allows Reinforcement Learning (RL) algorithms to use experience replay samples not only from human demonstrations but also successful transitions generated by RL…

Adaptive scaffolding enhances learning, yet the field lacks robust methods for measuring it within authentic tutoring dialogue. This gap has become more pressing with the rise of remote human tutoring and large language model-based systems.…

Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling…

In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences.…

Recent rehearsal-free continual learning (CL) methods guided by prompts achieve strong performance on vision tasks with non-stationary data but remain resource-intensive, hindering real-world edge deployment. We introduce resource-efficient…

User consumption behavior data, which records individuals' online spending history at various types of stores, has been widely used in various applications, such as store recommendation, site selection, and sale forecasting. However, its…

Retrieval-Augmented Generation (RAG) systems rely on retrieving relevant evidence from a corpus to support downstream generation. The common practice of splitting a long document into multiple shorter passages enables finer-grained and…

Industry-scale recommender systems face a core challenge: representing entities with high cardinality, such as users or items, using dense embeddings that must be accessible during both training and inference. However, as embedding sizes…

Most recently proposed methods for Neural Program Induction work under the assumption of having a large set of input/output (I/O) examples for learning any underlying input-output mapping. This paper aims to address the problem of data and…