Related papers: State Transfer Reveals Reuse in Controlled Routing
Predictive Quality of Service (PQoS) makes it possible to anticipate QoS changes, e.g., in wireless networks, and trigger appropriate countermeasures to avoid performance degradation. Hence, PQoS is extremely useful for automotive…
We study the routing of quantum information in qubit chains. This task is achieved by suitably chosen time-dependent local fields acting on the qubits. Employing the physics of coherent destruction of tunneling, we demonstrate that a…
This paper investigates the use of Infrastructure-To-Vehicle (I2V) communication to generate routing suggestions for drivers in transportation systems, with the goal of optimizing a measure of overall network congestion. We define link-wise…
In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk…
We study the problem of implementing arbitrary permutations of qubits under interaction constraints in quantum systems that allow for arbitrarily fast local operations and classical communication (LOCC). In particular, we show examples of…
Transit agencies that operate on-demand transportation services have to respond to trip requests from passengers in real time, which involves solving dynamic vehicle routing problems with pick-up and drop-off constraints. Based on…
Strong inductive biases enable learning from little data and help generalization outside of the training distribution. Popular neural architectures such as Transformers lack strong structural inductive biases for seq2seq NLP tasks on their…
Learning robot skills from scratch is often time-consuming, while reusing data promotes sustainability and improves sample efficiency. This study investigates policy transfer across different robotic platforms, focusing on peg-in-hole task…
The efficacy of a communication network hinges upon both its physical architecture and the protocols that are employed within it. In the context of quantum communications, there exists a fundamental rate-loss tradeoff for point-to-point…
Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…
In this paper, we propose a framework for the longitudinal control of connected and automated vehicles traveling in mixed traffic consisting of connected and non-connected human-driven vehicles. Reactive and predictive controllers are…
Network routing is a distributed decision problem which naturally admits numerical performance measures, such as the average time for a packet to travel from source to destination. OLPOMDP, a policy-gradient reinforcement learning…
Addressing the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios, this paper proposes a Transformer$^{-1}$ architecture based on the principle of deep adaptivity. This architecture achieves…
Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples,…
Transformer architectures, capable of capturing sequential dependencies in the history of user interactions, have become the dominant approach in sequential recommender systems. Despite their success, such models consider sequence elements…
Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications. Existing approaches…
The distributed control systems are more and more used in many industrial applications. These systems are often referred as "Networked control systems". The goal of this paper is to show the network influence on feedback control systems.…
In this paper, we study the longitudinal control problem for a platoon of vehicles with unknown nonlinear dynamics under both the predecessor-following and the bidirectional control architectures. The proposed control protocols are fully…
Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards)…
Emerging deployments of Generative AI increasingly execute inference across decentralized and heterogeneous edge devices rather than on a single trusted server. In such environments, a single device failure or misbehavior can disrupt the…