arxiv_cv
Abstract: Abstract: Recent advancements in text-to-3D generation have shown remarkable results by
leveraging 3D priors in combination with 2D diffusion. However, previous
methods utilize 3D priors that lack detailed and complex structural
information, limiting...
#3D Content Generation#Generative Modeling#Computer Graphics#AI for Design#Deep Learning
arxiv_cv
Abstract: Abstract: Enabling image generation models to be spatially controlled is an important
area of research, empowering users to better generate images according to their
own fine-grained specifications via e.g. edge maps, poses. Although this task
has se...
#Generative Models#Image Synthesis#Conditional Generation#Computer Vision#Deep Learning Architectures
arxiv_cv
Abstract: Abstract: The scarcity of data in various scenarios, such as medical, industry and
autonomous driving, leads to model overfitting and dataset imbalance, thus
hindering effective detection and segmentation performance. Existing studies
employ the gene...
#Generative AI#Data Augmentation#Domain Adaptation#Computer Vision#Deep Learning
arxiv_ml
Abstract: Abstract: Template-based molecular generation offers a promising avenue for drug design
by ensuring generated compounds are synthetically accessible through predefined
reaction templates and building blocks. In this work, we tackle three core
challen...
#Generative Models#Molecular Design#Drug Discovery#Reinforcement Learning#Optimization
arxiv_cv
Abstract: Abstract: Shot assembly is a crucial step in film production and video editing,
involving the sequencing and arrangement of shots to construct a narrative,
convey information, or evoke emotions. Traditionally, this process has been
manually executed ...
#Generative AI#Video Editing#Computational Creativity#Large Language Models#Machine Learning for Media#Narrative Generation
arxiv_ml
Abstract: Abstract: Machine learning-assisted diagnosis shows promise, yet medical imaging
datasets are often scarce, imbalanced, and constrained by privacy, making data
augmentation essential. Classical generative models typically demand extensive
computation...
#Generative Models#Medical Imaging#Quantum Computing#Deep Learning#Data Augmentation
arxiv_cv
Abstract: Abstract: We present IllumFlow, a novel framework that synergizes conditional Rectified
Flow (CRF) with Retinex theory for low-light image enhancement (LLIE). Our
model addresses low-light enhancement through separate optimization of
illumination and...
#Computer Vision#Image Processing#Generative Models#Deep Learning#Low-light Imaging
arxiv_ml
Abstract: Abstract: Part of the success of diffusion models stems from their ability to perform
iterative refinement, i.e., repeatedly correcting outputs during generation.
However, modern masked discrete diffusion lacks this capability: when a token
is genera...
#Generative Models#Diffusion Models#Natural Language Generation#Image Generation#Model Scaling
arxiv_ml
Abstract: Abstract: We propose the use of the ``spin-opstring", derived from Stochastic Series
Expansion Quantum Monte Carlo (QMC) simulations as machine learning (ML) input
data. It offers a compact, memory-efficient representation of QMC simulation
cells, co...
#Quantum Many-Body Physics#Machine Learning#Statistical Mechanics#Computational Physics#Generative Models (for data representation)
arxiv_ml
Abstract: Abstract: We present ProbHardE2E, a probabilistic forecasting framework that
incorporates hard operational/physical constraints, and provides uncertainty
quantification. Our methodology uses a novel differentiable probabilistic
projection layer (DPPL...
#Probabilistic Modeling#Forecasting#Constraint Satisfaction#Machine Learning#Uncertainty Quantification
arxiv_ml
Abstract: Abstract: Kernel discrepancies are a powerful tool for analyzing worst-case errors in
quasi-Monte Carlo (QMC) methods. Building on recent advances in optimizing such
discrepancy measures, we extend the subset selection problem to the setting of
kerne...
#Numerical Integration#Sampling Theory#Kernel Methods#Monte Carlo Methods#Discrepancy Theory
arxiv_ml
Abstract: Abstract: We present a detailed study of Bayesian inference workflows for pulsar timing
array data with a focus on enhancing efficiency, robustness and speed through
the use of normalizing flow-based nested sampling. Building on the Enterprise
framew...
#Bayesian Inference#Computational Astrophysics#Machine Learning#Generative Models#Statistical Methods
arxiv_ml
Abstract: Abstract: We study the problem of preconditioning in sequential prediction. From the
theoretical lens of linear dynamical systems, we show that convolving the
target sequence corresponds to applying a polynomial to the hidden transition
matrix. Build...
#Sequential Prediction#Time Series Analysis#Machine Learning Theory#Optimization#Control Theory
arxiv_ml
Abstract: Abstract: Simulation-based problems involving mixed-variable inputs frequently feature
domains that are hierarchical, conditional, heterogeneous, or tree-structured.
These characteristics pose challenges for data representation, modeling, and
optimiz...
#Design Optimization#Machine Learning#Surrogate Modeling#Optimization Theory#Data Representation
arxiv_ml
Abstract: Abstract: Tracking the solution of time-varying variational inequalities is an
important problem with applications in game theory, optimization, and machine
learning. Existing work considers time-varying games or time-varying
optimization problems. F...
#Optimization Theory#Game Theory#Dynamical Systems#Mathematical Analysis#Machine Learning Theory
arxiv_ml
Abstract: Abstract: Traditional neural networks, while powerful, rely on biologically implausible
learning mechanisms such as global backpropagation. This paper introduces the
Structurally Adaptive Predictive Inference Network (SAPIN), a novel
computational mo...
#Computational Neuroscience#Artificial Neural Networks#Biologically Plausible Learning#Control Systems#Generative Models
arxiv_ml
Abstract: Abstract: In recent years, diffusion models trained on equilibrium molecular
distributions have proven effective for sampling biomolecules. Beyond direct
sampling, the score of such a model can also be used to derive the forces that
act on molecular ...
#Generative Modeling#Molecular Simulation#Machine Learning for Science#Physics-Informed ML#Stochastic Processes
arxiv_ml
Abstract: Abstract: Critical heat flux (CHF) marks the onset of boiling crisis in light-water
reactors, defining safe thermal-hydraulic operating limits. To support Phase II
of the OECD/NEA AI/ML CHF benchmark, which introduces spatially varying power
profiles...
#Nuclear Engineering#Thermal-Hydraulics#Machine Learning Applications#Data Science
arxiv_ml
Abstract: Abstract: We study the complexity of online stochastic gradient descent (SGD) for
learning a two-layer neural network with $P$ neurons on isotropic Gaussian
data: $f_*(\boldsymbol{x}) = \sum_{p=1}^P a_p\cdot
\sigma(\langle\boldsymbol{x},\boldsymbol{v...
#Machine Learning Theory#Optimization Theory#Deep Learning Theory#Neural Network Dynamics#Statistical Learning Theory
arxiv_ml
Abstract: Abstract: The emergence of Deep Neural Networks (DNNs) in mission- and safety-critical
applications brings their reliability to the front. High performance demands of
DNNs require the use of specialized hardware accelerators. Systolic array
architect...
#Hardware Acceleration#Computer Architecture#Deep Learning Hardware#Reliable Computing#Embedded Systems
arxiv_ml
Abstract: Abstract: A diffusion probabilistic model (DPM) is a generative model renowned for its
ability to produce high-quality outputs in tasks such as image and audio
generation. However, training DPMs on large, high-dimensional datasets such as
high-resolu...
#Generative Modeling#Quantum Computing#Algorithm Design#Computational Efficiency
arxiv_ml
Abstract: Abstract: We study a compositional variant of kernel ridge regression in which the
predictor is applied to a coordinate-wise reweighting of the inputs. Formulated
as a variational problem, this model provides a simple testbed for feature
learning in ...
#Machine Learning Theory#Kernel Methods#Feature Learning#Optimization
arxiv_ml
Abstract: Abstract: Structure-based drug design (SBDD), aiming to generate 3D molecules with high
binding affinity toward target proteins, is a vital approach in novel drug
discovery. Although recent generative models have shown great potential, they
suffer fr...
#Computational Chemistry#Drug Discovery#Generative Models#Machine Learning for Science
arxiv_ml
Abstract: Abstract: Time-series forecasting increasingly demands not only accurate observational
predictions but also causal forecasting under interventional and counterfactual
queries in multivariate systems. We present DoFlow, a flow based generative
model d...
#Causal Inference#Time Series Analysis#Generative Models#Probabilistic Modeling#Forecasting
arxiv_ml
Abstract: Abstract: We give a pair of algorithms that efficiently learn a quantum state prepared
by Clifford gates and $O(\log n)$ non-Clifford gates. Specifically, for an
$n$-qubit state $|\psi\rangle$ prepared with at most $t$ non-Clifford gates,
our algorit...
#Quantum Information Theory#Quantum Machine Learning#Quantum Computing Algorithms#Quantum State Tomography
arxiv_ml
Abstract: Abstract: We examine the extent to which sublinear-sample property testing and
estimation apply to settings where samples are independently but not
identically distributed. Specifically, we consider the following distributional
property testing frame...
#Statistical Learning Theory#Distributional Property Testing#Non-i.i.d. Learning#Computational Statistics
arxiv_ml
Abstract: Abstract: The increasing use of generative ML foundation models for image restoration
tasks such as super-resolution calls for robust and interpretable uncertainty
quantification methods. We address this need by presenting a novel approach
based on c...
#Generative AI#Image Restoration#Uncertainty Quantification#Model Interpretability
arxiv_ml
Abstract: Abstract: Recently, optimization on the Riemannian manifold have provided valuable
insights to the optimization community. In this regard, extending these methods
to to the Wasserstein space is of particular interest, since optimization on
Wasserstei...
#Optimization#Machine Learning Theory#Stochastic Processes#Geometric Deep Learning#Sampling Methods
arxiv_ml
Abstract: Abstract: This work addresses the problem of efficient sampling of Markov random fields
(MRF). The sampling of Potts or Ising MRF is most often based on Gibbs
sampling, and is thus computationally expensive. We consider in this work how
to circumvent...
#Probabilistic Graphical Models#Sampling Techniques#Model Efficiency#Statistical Inference
arxiv_ml
Abstract: Abstract: We prove that the Gibbs states of classical, and commuting-Pauli,
Hamiltonians are stable under weak local decoherence: i.e., we show that the
effect of the decoherence can be locally reversed. In particular, our
conclusions apply to finite...
#Quantum Information#Statistical Mechanics#AI Safety#Generative Models#Theoretical Physics