Related papers: Continual Model Routing in Evolving Model Hubs

Continual learning, especially class-incremental learning (CIL), on the basis of a pre-trained model (PTM) has garnered substantial research interest in recent years. However, how to effectively learn both discriminative and comprehensive…

Complex real-life routing challenges can be modeled as variations of well-known combinatorial optimization problems. These routing problems have long been studied and are difficult to solve at scale. The particular setting may also make…

AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system that maps tasks to the appropriate strategies is crucial.…

Motivated by the promising advances of deep-reinforcement learning (DRL) applied to cooperative multi-agent systems we propose a model and learning procedure to solve the Capacitated Multi-Vehicle Routing Problem (CMVRP) with fixed fleet…

Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric…

Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid…

Continual learning could shift the machine learning paradigm from data centric to model centric. A continual learning model needs to scale efficiently to handle semantically different datasets, while avoiding unnecessary growth. We…

Exploring machine learning techniques for addressing vehicle routing problems has attracted considerable research attention. To achieve decent and efficient solutions, existing deep models for vehicle routing problems are typically trained…

Despite the success of AI-enabled onboard perception, on-ramp merging has been one of the main challenges for autonomous driving. Due to limited sensing range of onboard sensors, a merging vehicle can hardly observe main road conditions and…

In-network caching is likely to become an integral part of various networked systems (e.g., 5G networks, LPWAN and IoT systems) in the near future. In this paper, we compare and contrast model-based and machine learning approaches for…

The burgeoning volume of multi-modal data necessitates advanced retrieval paradigms beyond unimodal and cross-modal approaches. Composed Multi-modal Retrieval (CMR) emerges as a pivotal next-generation technology, enabling users to query…

Connected Autonomous Vehicles (CAVs) promise to reduce congestion in future urban networks, potentially by optimizing their routing decisions. Unlike for human drivers, these decisions can be made with collective, data-driven policies,…

Scaling a Search Conversion Rate (CVR) prediction model, especially in high-traffic environments, presents a challenge: superior model quality needs to be balanced with strict constraints on training cost and serving latency. This paper…

Continual learning the ability of a neural network to learn multiple sequential tasks without catastrophic forgetting remains a central challenge in developing adaptive artificial intelligence systems. While deep learning models achieve…

Learning-based autonomous driving requires continuous integration of diverse knowledge in complex traffic , yet existing methods exhibit significant limitations in adaptive capabilities. Addressing this gap demands autonomous driving…

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing…

Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each…

Due to the rapidly increasing usage of personal mobile devices and the need of executing CVE applications in environments that have no previous network infrastructure, Mobile Collaborative Virtual Environments (MCVEs) systems will become…

We propose a feature-based guidance mechanism to enhance metaheuristic algorithms for solving the Capacitated Vehicle Routing Problem (CVRP). This mechanism leverages an Explainable AI (XAI) model to identify features that correlate with…