Related papers: OASI: Objective-Aware Surrogate Initialization for…
Direct fidelity estimation benefits from tailoring measurements to a fixed target, but the operator-aware shadow importance sampling (OASIS) method optimizes an outcome-wise linear-program surrogate rather than the exact worst-case variance…
Neurosymbolic AI (NSAI) has recently emerged to mitigate limitations associated with deep learning (DL) models, e.g. quantifying their uncertainty or reason with explicit rules. Hence, TinyML hardware will need to support these symbolic…
Recent vision-language-action (VLA) models and world action models (WAMs) advance robotic manipulation by enriching intermediate representations with auxiliary spatial features or future visual-state prediction. However, these…
The notion of expense in Bayesian optimisation generally refers to the uniformly expensive cost of function evaluations over the whole search space. However, in some scenarios, the cost of evaluation for black-box objective functions is…
As data collection and simulation capabilities advance, multi-modal learning, the task of learning from multiple modalities and sources of data, is becoming an increasingly important area of research. Surrogate models that learn from data…
Performing reliability analysis on complex systems is often computationally expensive. In particular, when dealing with systems having high input dimensionality, reliability estimation becomes a daunting task. A popular approach to overcome…
The expansion of machine learning into dynamic environments presents challenges in handling open-world problems where label shift, covariate shift, and unknown classes emerge. Post-training methods have been explored to address these…
A key drawback of the current generation of artificial decision-makers is that they do not adapt well to changes in unexpected situations. This paper addresses the situation in which an AI for aerial dog fighting, with tunable parameters…
Machine unlearning seeks to remove the influence of designated training data while preserving performance on the remaining data. Approximate unlearning can be viewed as a local editing problem; in min-max unlearning, the key local object is…
AI-assisted molecular optimization is a very active research field as it is expected to provide the next-generation drugs and molecular materials. An important difficulty is that the properties to be optimized rely on costly evaluations.…
Hardware-aware Neural Architecture Search (NAS) is one of the most promising techniques for designing efficient Deep Neural Networks (DNNs) for resource-constrained devices. Surrogate models play a crucial role in hardware-aware NAS as they…
To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpensively at inference time. Unfortunately, commonly used approaches, including supervised and…
Aerodynamic shape optimization in industry still faces challenges related to robustness and scalability. This aspect becomes crucial for advanced optimizations that rely on expensive high-fidelity flow solvers, where computational budget…
In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can…
While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant computational inefficiencies. Existing frameworks typically deploy large…
Evolutionary algorithms often struggle to find well converged (e.g small inverted generational distance on test problems) solutions to multi-objective optimization problems on a limited budget of function evaluations (here, a few hundred).…
The goal of this paper is to make Optimal Experimental Design (OED) computationally feasible for problems involving significant computational expense. We focus exclusively on the Mean Objective Cost of Uncertainty (MOCU), which is a…
The state of an object reflects its current status or condition and is important for a robot's task planning and manipulation. However, detecting an object's state and generating a state-sensitive plan for robots is challenging. Recently,…
We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibility but also…
Wireless sensor networks require accurate target localization, often achieved through received signal strength (RSS) localization estimation based on maximum likelihood (ML). However, ML-based algorithms can suffer from issues such as low…