Related papers: Symbol Resolution MatRs: Make it Fast and Observab…

Fine-tuning pretrained language models can improve task performance while subtly altering the evidence a model relies on. We propose a training-time interpretability view that tracks token-level attributions across finetuning epochs. We…

Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and…

Recommending routes by their probability of having a rider has long been the goal of conventional route recommendation systems. While this maximizes the platform-specific criteria of efficiency, it results in sub-optimal outcomes with the…

Many software engineering techniques, such as fault localization, operate based on relevance relationships between tests and code. These relationships are often inferred through the use of dynamic test execution information (test execution…

Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the…

It was suggested that a programmable matter system (composed of multiple computationally weak mobile particles) should remain connected at all times since otherwise, reconnection is difficult and may be impossible. At the same time, it was…

In this paper, we investigate the use of variable speed limits for resilient operation of transportation networks, which are modeled as dynamical flow networks under local routing decisions. In such systems, some external inflow is injected…

Network regularization is an effective tool for incorporating structural prior knowledge to learn coherent models over networks, and has yielded provably accurate estimates in applications ranging from spatial economics to neuroimaging…

Resilience broadly describes a quality of withstanding perturbations. Measures of system resilience have gathered increasing attention across applied disciplines, yet existing metrics often lack computational accessibility and…

Self-adjusting computation is an approach for automatically producing dynamic algorithms from static ones. The approach works by tracking control and data dependencies, and propagating changes through the dependencies when making an update.…

Modern web applications replicate their data across the globe and require strong consistency guarantees for their most critical data. These guarantees are usually provided via state-machine replication (SMR). Recent advances in SMR have…

Issue-commit linking, which connects issues with commits that fix them, is crucial for software maintenance. Existing approaches have shown promise in automatically recovering these links. Evaluations of these techniques assess their…

Optimization-based decision support systems have a significant potential to reduce delays, and thus improve efficiency on the railways, by automatically re-routing and re-scheduling trains after delays have occurred. The operations research…

Symbolic representations have been used successfully in off-line planning algorithms for Markov decision processes. We show that they can also improve the performance of on-line planners. In addition to reducing computation time, symbolic…

Modern networked systems are increasingly reconfigurable, enabling demand-aware infrastructures whose resources can be adjusted according to the workload they currently serve. Such dynamic adjustments can be exploited to improve network…

The "Locate-then-Update" paradigm has become a predominant approach in the post-training of large language models (LLMs), identifying critical components via mechanistic interpretability for targeted parameter updates. However, this…

The prediction of both the existence and weight of network links at future time points is essential as complex networks evolve over time. Traditional methods, such as vector autoregression and factor models, have been applied to small,…

Machine-learning technologies for learning dynamical systems from data play an important role in engineering design. This research focuses on learning continuous linear models from data. Stability, a key feature of dynamic systems, is…

The sequential semantics of many concurrent data structures, such as stacks and queues, inevitably lead to memory contention in parallel environments, thus limiting scalability. Semantic relaxation has the potential to address this issue,…

Pushdown systems (PDSs) and recursive state machines (RSMs), which are linearly equivalent, are standard models for interprocedural analysis. Yet RSMs are more convenient as they (a) explicitly model function calls and returns, and (b)…