相关论文: State Transfer Reveals Reuse in Controlled Routing

Human drivers' control quality in the first seconds after a handover is critical to shared-driving safety; potentially unsafe steering or pedal inputs therefore require detection and correction by the automated vehicle's safety-fallback…

In the physical design of integrated circuits, global and detailed routing are critical stages involving the determination of the interconnected paths of each net on a circuit while satisfying the design constraints. Existing actual routers…

We present PRISM (Policy Reuse via Interpretable Strategy Mapping), a framework that grounds reinforcement learning agents' decisions in discrete, causally validated concepts and uses those concepts as a zero-shot transfer interface between…

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

This paper proposes a reinforcement learning-based approach for optimal transient frequency control in power systems with stability and safety guarantees. Building on Lyapunov stability theory and safety-critical control, we derive…

Controllability refers to a situation in which a Multi-agent System may be steered from one state to another using specified rules. As a result, there is belief in achieving a given condition by explicit advances. The level of dynamism in…

Background: In settings where proof-of-principle trials have succeeded but the effectiveness of different forms of implementation remains uncertain, trials that not only generate information about intervention effects but also provide…

In networks of independent entities that face similar predictive tasks, transfer machine learning enables to re-use and improve neural nets using distributed data sets without the exposure of raw data. As the number of data sets in business…

Single node failures represent more than 85% of all node failures in the today's large communication networks such as the Internet. Also, these node failures are usually transient. Consequently, having the routing paths globally recomputed…

This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training…

Reliable path planning in stochastic transportation networks requires decisions that account for uncertain and correlated travel times on irregular road graphs, rather than only minimizing expected delay. Such networks exhibit strong…

Transfer learning in deep reinforcement learning is often motivated by improved stability and reduced training cost, but it can also fail under substantial domain shift. This paper presents a controlled empirical study examining how…

Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interface: adaptation through examples. For deterministic…

Neural combinatorial optimization (NCO) is a promising learning-based approach to solving various vehicle routing problems without much manual algorithm design. However, the current NCO methods mainly focus on the in-distribution…

Cooperation emergence in multi-agent systems represents a fundamental statistical physics problem where microscopic learning rules drive macroscopic collective behavior transitions. We propose a Q-learning-based variant of adaptive rewiring…

Recent works found that fine-tuning and joint training---two popular approaches for transfer learning---do not always improve accuracy on downstream tasks. First, we aim to understand more about when and why fine-tuning and joint training…

We present CREST, an approach for causal reasoning in simulation to learn the relevant state space for a robot manipulation policy. Our approach conducts interventions using internal models, which are simulations with approximate dynamics…

We propose $\textit{iterative inversion}$ -- an algorithm for learning an inverse function without input-output pairs, but only with samples from the desired output distribution and access to the forward function. The key challenge is a…

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…

Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow…