Related papers: From Atoms to Dynamics: Learning the Committor Wit…

Protein function does not solely depend on structure but often relies on dynamical transitions between distinct conformations. Despite this fact, our ability to characterize or predict protein dynamics is substantially less developed…

Extending spatio-temporal scale limitations of models for complex atomistic systems considered in biochemistry and materials science necessitates the development of enhanced sampling methods. The potential acceleration in exploring the…

Existing video captioning methods merely provide shallow or simplistic representations of object behaviors, resulting in superficial and ambiguous descriptions. However, object behavior is dynamic and complex. To comprehensively capture the…

The use of machine learning in chemistry has become a common practice. At the same time, despite the success of modern machine learning methods, the lack of data limits their use. Using a transfer learning methodology can help solve this…

Concept-based interpretations of black-box models are often more intuitive for humans to understand. The most widely adopted approach for concept-based interpretation is Concept Activation Vector (CAV). CAV relies on learning a linear…

In the interactive image segmentation task, the Particle Competition and Cooperation (PCC) model is fed with a complex network, which is built from the input image. In the network construction phase, a weight vector is needed to define the…

Precise reconstruction of top quark properties is a challenging task at the Large Hadron Collider due to combinatorial backgrounds and missing information. We introduce a physics-informed neural network architecture called the Covariant…

A central object in the computational studies of rare events is the committor function. Though costly to compute, the committor function encodes complete mechanistic information of the processes involving rare events, including reaction…

We propose to interpret machine learning functions as physical observables, opening up the possibility to apply "standard" statistical-mechanical methods to outputs from neural networks. This includes histogram reweighting and finite-size…

Molecular-level understanding of the interactions between the constituents of an atomic structure is essential for designing novel materials in various applications. This need goes beyond the basic knowledge of the number and types of…

Concept Activation Vectors (CAVs) offer insights into neural network decision-making by linking human friendly concepts to the model's internal feature extraction process. However, when a new set of CAVs is discovered, they must still be…

While recent advances in AI have transformed protein structure prediction, protein function is also strongly influenced by the thermodynamic and kinetic features encoded in its underlying free-energy surface. Here, we propose a…

The quantum perceptron, the variational circuit, and the Grover algorithm have been proposed as promising components for quantum machine learning. This paper presents a new quantum perceptron that combines the quantum variational circuit…

Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional…

A key challenge in deriving unified neural solvers for combinatorial optimization (CO) is efficient generalization of models between a given set of tasks to new tasks not used during the initial training process. To address it, we first…

Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph…

Complex Query Answering (CQA) over Knowledge Graphs (KGs) is a challenging task. Given that KGs are usually incomplete, neural models are proposed to solve CQA by performing multi-hop logical reasoning. However, most of them cannot perform…

Learning general-purpose models from diverse datasets has achieved great success in machine learning. In robotics, however, existing methods in multi-task learning are typically constrained to a single robot and workspace, while recent work…

Discrete structure rules for validating molecular structures are usually limited to fulfillment of the octet rule or similar simple deterministic heuristics. We propose a model, inspired by language modeling from natural language…

Complex human activity recognition (CHAR) remains a pivotal challenge within ubiquitous computing, especially in the context of smart environments. Existing studies typically require meticulous labeling of both atomic and complex…