Faithful Logic Embeddings in HOL -- A recipe to have it all: deep and shallow, automated and interactive, heavy and light, proofs and counterexamples, meta and object level
February 26, 2025
|
Computer Science
Mathematics
Logic in Computer Science
Artificial Intelligence
Logic
Logic in Computer Science
Artificial Intelligence
Logic
Deep and shallow embeddings of non-classical logics in classical higher-order
logic have been explored, implemented, and used in various automated reasoning
tools in recent years. This paper presents a recipe for the simultaneous
deployment...
Extremely Greedy Equivalence Search
February 26, 2025
| | |
Computer Science
Statistics
Machine Learning
Machine Learning
Machine Learning
Machine Learning
The goal of causal discovery is to learn a directed acyclic graph from data.
One of the most well-known methods for this problem is Greedy Equivalence
Search (GES). GES searches for the graph by incrementally and greedily adding
or removing...
Advancing calibration for stochastic agent-based models in epidemiology with Stein variational inference and Gaussian process surrogates
February 26, 2025
| | | | | | | | |
Statistics
Computer Science
Machine Learning
Machine Learning
Machine Learning
Machine Learning
Accurate calibration of stochastic agent-based models (ABMs) in epidemiology
is crucial to make them useful in public health policy decisions and
interventions. Traditional calibration methods, e.g., Markov Chain Monte Carlo
(MCMC), that yi...
Recorded Versus Synthetic Ground Motions: A Comparative Analysis of Structural Seismic Responses
February 26, 2025
| | | | | | |
Physics
Statistics
Geophysics
Applications
Geophysics
Applications
This paper presents a comparative analysis of structural seismic responses
under two types of ground motion inputs: (i) synthetic motions generated by
stochastic ground motion models and (ii) recorded motions from an earthquake
database. Fi...
When Large Language Models Meet Speech: A Survey on Integration Approaches
February 26, 2025
| | | | | | |
Computer Science
Electrical Engineering and Systems Science
Computation and Language
Sound
Audio and Speech Processing
Computation and Language
Sound
Audio and Speech Processing
Recent advancements in large language models (LLMs) have spurred interest in
expanding their application beyond text-based tasks. A large number of studies
have explored integrating other modalities with LLMs, notably speech modality,
which...
Codimension one defects in free scalar field theory
February 26, 2025
| | | | |
Physics
High Energy Physics - Theory
High Energy Physics - Theory
We study various aspects of codimension one defects in free scalar field
theory, with particular emphasis on line defects in two-dimensions. These
defects are generically non-conformal, but include conformal and topological
defects as speci...
Repurposing the scientific literature with vision-language models
February 26, 2025
| | | | | | | | | | and others
Computer Science
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Human-Computer Interaction
Research in AI for Science often focuses on using AI technologies to augment
components of the scientific process, or in some cases, the entire scientific
method; how about AI for scientific publications? Peer-reviewed journals are
foundati...
Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents
February 26, 2025
| | | | | | | | | | and others
Computer Science
Computation and Language
Artificial Intelligence
Machine Learning
Computation and Language
Artificial Intelligence
Machine Learning
The deployment of Large Language Models (LLMs) in customer support is
constrained by hallucination-generating false information-and the high cost of
proprietary models. To address these challenges, we propose a
retrieval-augmented question-...
Generalist World Model Pre-Training for Efficient Reinforcement Learning
February 26, 2025
| | | | | | | | | | and others
Computer Science
Machine Learning
Robotics
Machine Learning
Robotics
Sample-efficient robot learning is a longstanding goal in robotics. Inspired
by the success of scaling in vision and language, the robotics community is now
investigating large-scale offline datasets for robot learning. However,
existing me...
High-fidelity Multiphysics Modelling for Rapid Predictions Using Physics-informed Parallel Neural Operator
February 26, 2025
| | | | | | | | |
Computer Science
Mathematics
Physics
Machine Learning
Numerical Analysis
Numerical Analysis
Computational Physics
Machine Learning
Numerical Analysis
Numerical Analysis
Computational Physics
Modelling complex multiphysics systems governed by nonlinear and strongly
coupled partial differential equations (PDEs) is a cornerstone in computational
science and engineering. However, it remains a formidable challenge for
traditional nu...