Related papers: DRAE: Dynamic Retrieval-Augmented Expert Networks …

Pick-up and Delivery Route Prediction (PDRP), which aims to estimate the future service route of a worker given his current task pool, has received rising attention in recent years. Deep neural networks based on supervised learning have…

Autonomous navigation capabilities play a critical role in service robots operating in environments where human interactions are pivotal, due to the dynamic and unpredictable nature of these environments. However, the variability in human…

We introduce a methodology for designing and training deep neural networks (DNN) that we call "Deep Regression Ensembles" (DRE). It bridges the gap between DNN and two-layer neural networks trained with random feature regression. Each layer…

Enabling large-scale generative models to continuously learn new visual concepts is essential for personalizing pre-trained models to meet individual user preferences. Existing approaches for continual visual concept learning are…

Deep Reinforcement Learning (DRL) has been highly effective in learning from and adapting to RF environments and thus detecting and mitigating jamming effects to facilitate reliable wireless communications. However, traditional DRL methods…

Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, conflicting between internal and external retrieved contexts, or…

Pretraining on a large-scale corpus has become a standard method to build general language models (LMs). Adapting a model to new data distributions targeting different downstream tasks poses significant challenges. Naive fine-tuning may…

Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…

Understanding how the brain responds to sensory inputs is challenging: brain recordings are partial, noisy, and high dimensional; they vary across sessions and subjects and they capture highly nonlinear dynamics. These challenges have led…

Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to distributed training, and modularity. Previous research has illustrated that MoEs can significantly…

Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting previously acquired abilities. Existing approaches either internalize knowledge by…

Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental learning, large domain shifts intensify the…

Deep reinforcement learning (DRL) has become a powerful tool for complex decision-making in machine learning and AI. However, traditional methods often assume perfect action execution, overlooking the uncertainties and deviations between an…

Deep Reinforcement Learning (DRL) is a powerful framework for solving complex sequential decision-making problems, particularly in robotic control. However, its practical deployment is often hindered by the substantial amount of experience…

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial…

Dynamic Rank Reinforcement Learning (DR-RL) approximations rely on static rank assumptions, limiting their flexibility across diverse linguistic contexts. Our method dynamically modulates ranks based on real-time sequence dynamics,…

In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture of individual…

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing research focuses on…

Mixture of Experts (MoE) architectures have recently advanced the scalability and adaptability of large language models (LLMs) for continual multimodal learning. However, efficiently extending these models to accommodate sequential tasks…

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct…