Related papers: AFLL: Real-time Load Stabilization for MMO Game Se…

In large language model (LLM) serving systems, executing each request consists of two phases: the compute-intensive prefill phase and the memory-intensive decoding phase. To prevent performance interference between the two phases, current…

Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs…

Several multiagent reinforcement learning (MARL) algorithms have been proposed to optimize agents decisions. Due to the complexity of the problem, the majority of the previously developed MARL algorithms assumed agents either had some…

Federated Learning (FL) facilitates collaborative model training across distributed clients while ensuring data privacy. Traditionally, FL relies on a centralized server to coordinate learning, which creates bottlenecks and a single point…

Large Language Models (LLMs) pre-trained on internet-scale datasets have shown impressive capabilities in code understanding, synthesis, and general purpose question-and-answering. Key to their performance is the substantial prior knowledge…

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Federated Continual Learning (FCL) has emerged as a promising paradigm that combines Federated Learning (FL) and Continual Learning (CL). To achieve good model accuracy, FCL needs to tackle catastrophic forgetting due to concept drift over…

For effective matching of resources (e.g., taxis, food, bikes, shopping items) to customer demand, aggregation systems have been extremely successful. In aggregation systems, a central entity (e.g., Uber, Food Panda, Ofo) aggregates supply…

The Aircraft Landing Problem (ALP) is one of the challenging problems in aircraft transportation and management. The challenge is to schedule the arriving aircraft in a sequence so that the cost and delays are optimized. There are various…

The growing penetration of renewable and distributed generation is transforming power systems and challenging conventional protection schemes that rely on fixed settings and local measurements. Machine learning (ML) offers a data-driven…

Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods…

We introduce CAMRL, the first curriculum-based asymmetric multi-task learning (AMTL) algorithm for dealing with multiple reinforcement learning (RL) tasks altogether. To mitigate the negative influence of customizing the one-off training…

This dissertation explores the application of multi-agent reinforcement learning (MARL) for handling deadlocks in intralogistics systems that rely on autonomous mobile robots (AMRs). AMRs enhance operational flexibility but also increase…

Online event-based perception techniques on board robots navigating in complex, unstructured, and dynamic environments can suffer unpredictable changes in the incoming event rates and their processing times, which can cause computational…

Efficient traffic control (TSC) is essential for urban mobility, but traditional systems struggle to handle the complexity of real-world traffic. Multi-agent Reinforcement Learning (MARL) offers adaptive solutions, but online MARL requires…

Load balancing systems, comprising a central dispatcher and a scheduling policy at each server, are widely used in practice, and their response time has been extensively studied in the theoretical literature. While much is known about the…

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios requires meeting…

Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge. In this paper, we propose MoRAL, i.e., Mixture-of-Experts augmented Low-Rank Adaptation for Lifelong…

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by…