相关论文: State Transfer Reveals Reuse in Controlled Routing

To support N-1 pre-fault transient stability assessment, this paper introduces a new data collection method in a data-driven algorithm incorporating the knowledge of power system dynamics. The domain knowledge on how the disturbance effect…

Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task. Transfer RL methods can…

Transformer hidden states are often interpreted through local or low-order objects: neurons, sparse features, attention heads, residual-stream directions, or activation patches. This paper studies a complementary object: the rank-indexed…

Prompt injection poses a critical threat to the safe deployment of large language models, yet existing detection approaches are typically evaluated under limited settings that do not reflect real-world operating constraints. In this work,…

While deep learning has revolutionized research and applications in NLP and computer vision, this has not yet been the case for behavioral modeling and behavioral health applications. This is because the domain's datasets are smaller, have…

In this paper, we develop a theoretical framework for goal-oriented communication assisted by reconfigurable meta-surfaces in the context of networked control systems. The relation to goal-oriented communication stems from the fact that…

We investigate congestion-aware control of quantum repeater nodes operating under stochastic traffic and finite memory coherence. Entanglement generation is modeled as a probabilistic process producing Werner states subject to depolarizing…

Quantum networks consist of quantum nodes that are linked by entanglement and quantum information can be transferred from one node to another. Operations can be applied to qubits of local nodes coordinated by classical communication to…

We analyze how the knowledge to autonomously handle one type of intersection, represented as a Deep Q-Network, translates to other types of intersections (tasks). We view intersection handling as a deep reinforcement learning problem, which…

Prompt tuning offers a parameter-efficient way to adapt large pre-trained language models to new tasks, but most existing approaches are designed for single-task settings, failing to share knowledge across related tasks. We propose…

Feedback dynamic routing is a commonly used control strategy in transportation systems. This class of control strategies relies on real-time information about the traffic state in each link. However, such information may not always be…

The implementation of a quantum router capable of performing both quantum signal routing and quantum addressing (a Q2-router) represents a key step toward building quantum networks and quantum random access memories. We realize a Q2-router…

Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to…

We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a \emph{target task}. We propose a…

Model routing determines whether to use an accurate black-box model or a simpler surrogate that approximates it at lower cost or greater interpretability. In deployment settings, practitioners often wish to restrict surrogate use to inputs…

Trajectory planning in autonomous driving is highly dependent on predicting the emergent behavior of other road users. Learning-based methods are currently showing impressive results in simulation-based challenges, with transformer-based…

We present a Real-Time Operator Takeover (RTOT) paradigm that enables operators to seamlessly take control of a live visuomotor diffusion policy, guiding the system back to desirable states or providing targeted corrective demonstrations.…

Scalable quantum information processing will require quantum networks of qubits with the ability to coherently transfer quantum states between the desired sender and receiver nodes. Here we propose a scheme to implement a quantum router…

Developing robust models to accurately predict the trajectories of surrounding agents is fundamental to autonomous driving safety. However, most public datasets, such as the Waymo Open Motion Dataset and Argoverse, are collected in Western…

Distributed systems have become increasingly prevalent in the software industry. Due to their intrinsic complexity, much research has focused on the verification of their behaviour. An active research line is around behaviour models that…