A new diffusion model generates novel protein backbones without relying on pretrained networks.
problem Generating novel protein backbones without relying on pretrained networks.
method Developed a SE(3) invariant diffusion model on multiple frames, called FrameDiff.
result Generated designable protein monomers up to 500 amino acids without pretrained networks.
Study on Langevin dynamics on planar motion group, highlighting geometric mechanism.
problem Understanding Langevin dynamics on the Lie group SE(2).
method Intrinsic formulation on SE(2), using invariant vector fields and natural projection.
result Effective macroscopic diffusion on R^2 emerges through averaging.
Improved speech enhancement using diffusion models with MSE loss.
problem Efficient incorporation of noisy speech in generative speech enhancement.
method Augmented diffusion-based generative model with a MSE loss for enhanced speech.
result Proposed method improves speech enhancement performance compared to original diffusion model.
EDGI improves sample efficiency and generalization in tasks with spatial and temporal symmetries.
problem Sample inefficiency and poor generalization in tasks with geometric symmetries.
method Equivariant Diffuser framework, SE(3)xZxSn-equivariant diffusion model.
result EDGI is more sample efficient and generalizes better than non-equivariant models.
An iterative SE(3)-Transformer model is developed for graph data.
problem Manipulating three-dimensional data with rotational and translational symmetries.
method Iterative SE(3)-equivariant attention mechanism applied to graph data.
result Iterative SE(3)-Transformer outperforms single-pass version on a toy problem.
Framework learns surrogates for molecular dynamics across multiple time-scales.
problem Stable molecular dynamics simulations require small time-steps, but long-time-scale moments need repeated simulations.
method Implicit Transfer Operator Learning with denoising diffusion probabilistic models and SE(3) equivariant architecture.
result Models can generate self-consistent stochastic dynamics across multiple time-scales.
New model simplifies symmetry handling in generative AI.
problem Symmetry handling in generative models for scientific tasks.
method Quotient-space diffusion models, viewing symmetry as quotient space.
result Improves performance over existing methods for molecular structure generation.
Study uses multidimensional SE-NBD process to analyze default portfolios and identify shock amplification.
problem Analyzing interactions and shock propagation in default portfolios with multiple sectors.
method Applied multidimensional self-exciting negative binomial distribution (SE-NBD) process to 13 sectors.
result Identified upstream and downstream sectors, showing shock amplification in default portfolios.
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
The statistically equivalent signature (SES) algorithm is a method for feature selection inspired by the principles of constrained-based learning of Bayesian Networks. Most of the currently available feature-selection methods return only a single subset of features, supposedly the one with the highest predictive power.…
Smooth SE structures on Sasaki-joins and Bott orbifolds constructed.
problem Constructing smooth Sasaki-Einstein structures on Sasaki-joins.
method Categorical relationship between Sasaki-joins and Bott orbifolds, explicit construction.
result Infinitely many smooth SE structures up to dimension eleven, conjecture for all odd dimensions.
Sep-SpectralNet improves SE for broader applicability and scalability.
problem Three main drawbacks of current SE implementations: generalizability, scalability, and eigenvectors separation.
method Sep-SpectralNet extends SpectralNet with an eigenvector separation post-processing step.
result Sep-SpectralNet achieves consistent SE approximation and generalization, enhancing scalability and applicability.
New method uses diffusion models to generate proteins with specific motifs.
problem Generating proteins with specific functional substructures (motifs) using diffusion models.
method Adapting SMC-aided diffusion posterior samplers to zero-shot scaffolding tasks.
result Proposed potentials and samplers improve performance in generating proteins with desired motifs.
A five dimensional Sasaki-Einstein (SE) manifold provides a AdS/CFT pair for four dimensional N=1 SCFT, and those pairs are very useful in studying field theory and AdS/CFT correspondence. The space of known SE manifolds is increased significantly in the last decade, and we initiated the study of various fi…
Study cohomological equation for robotic screw motions on SE(3).
problem Understanding obstruction phenomena in robotic rigid-body motion.
method Combining Fourier analysis and Peter-Weyl theory, reduce to finite-dimensional linear transport systems.
result Explicit screw motion illustrates resonance conditions and finite-dimensional obstructions.
Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks (GANs) in a variety of image processing tasks, we explore the potential of cond…
One of the ways to train deep neural networks effectively is to use residual connections. Residual connections can be classified as being either identity connections or bridge-connections with a reshaping convolution. Empirical observations on CIFAR-10 and CIFAR-100 datasets using a baseline Resnet model, with bridge-c…
SE(3)-Transformers maintain equivariance for 3D data under rotations and translations.
problem Ensuring stable and predictable performance in 3D data under transformations.
method Introducing a self-attention module that is equivariant under continuous 3D roto-translations.
result The SE(3)-Transformer outperforms non-equivariant and non-attention models on real-world datasets.
Tiled Squeeze-and-Excite improves channel attention with local spatial context.
problem Improving channel attention mechanisms in neural networks.
method Proposes tiled squeeze-and-excite (TSE) framework for channel attention.
result Local context of 7 rows or columns is sufficient for matching global context performance.
Closed-form relations and approximations for SE(3) derivatives for robust numerical simulations.
problem Deriving closed-form derivatives and approximations for SE(3) for robust numerical simulations.
method Avoiding block partitioning, deriving higher-order approximations for differential, first and second derivatives, Jacobian, and Hessian.
result Compact and numerically robust closed-form relations for SE(3) derivatives.
SE-RRMs solve structured problems like Sudoku and ARC-AGI by enforcing symbol equivariance.
problem Structured reasoning problems like Sudoku and ARC-AGI.
method Symbol-equivariant recurrent reasoning models enforcing permutation equivariance.
result SE-RRMs outperform prior RRMs on 9x9 Sudoku and generalize to larger and smaller instances.
Most recent studies on deep learning based speech enhancement (SE) focused on improving denoising performance. However, successful SE applications require striking a desirable balance between denoising performance and computational cost in real scenarios. In this study, we propose a novel parameter pruning (PP) techniq…
P-SE explains model decisions with minimal feature subsets and fast estimators.
problem Explain model decisions in regression and classification.
method Probabilistic Sufficient Explanations (P-SE) with random Forests for conditional probability estimation.
result Consistent and efficient explanations for regression and classification models.
Artificial neural network (ANN) provides superior accuracy for nonlinear alternating current (AC) state estimation (SE) in smart grid over traditional methods. However, research has discovered that ANN could be easily fooled by adversarial examples. In this paper, we initiate a new study of adversarial false data injec…
We use self-report and electrodermal activity (EDA) wearable sensor data from 77 nights of sleep on six participants to test the efficacy of EDA data for sleep monitoring. We used factor analysis to find latent factors in the EDA data, and causal model search to find the most probable graphical model accounting for sel…
Replication study shows Deep-SE still not as effective as previously thought for agile effort estimation.
problem Improving accuracy in estimating agile software development effort.
method Close replication of Deep-SE using additional data and comparison with multiple baselines.
result Deep-SE outperforms only a few cases, suggesting more work is needed.
Researchers find metric lines in SE(2) using Hamilton-Jacobi theory.
problem Identifying metric lines in the Special Euclidean group on the plane.
method Alternative proof using Hamilton-Jacobi theory.
result Metric lines in SE(2) are identified.
We propose a notion of distance between two parametrized planar curves, called their discrepancy, and defined intuitively as the minimal amount of deformation needed to deform the source curve into the target curve. A precise definition of discrepancy is given as follows. A curve of transformations in the special Eucli…
Using the basic Lie symmetry method, we find the most general Lie point symmetries group of the ∇u=f(u) Poisson's equation, which has a subalgebra isomorphic to the 3−dimensional special Euclidean group SE(3) or group of rigid motions of R3. Looking the adjoint representation of ${\rm SE}(3)…
MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.
problem Learning from multiple suboptimal experts in reinforcement learning.
method Active policy improvement from multiple black-box oracles.
result MAPS and MAPS-SE achieve sample efficiency and state-wise imitation learning.
This paper summarizes closed-form relations for SE(3) maps and their derivatives.
problem Closed-form expressions for SE(3) maps and their derivatives are scattered in the literature.
method Summarizes and provides proofs for relevant closed-form relations of the exponential and Cayley map on SE(3).
result Provides an implicit generalized-alpha scheme for rigid/flexible multibody systems using the Cayley map.
Improved scaffold generation for protein motifs using SE(3) flow matching.
problem Lack of structural diversity in generated scaffolds for protein motifs.
method Extended FrameFlow for motif-scaffolding with motif amortization and motif guidance.
result 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art.
Proposes SE(3) equivariant graph neural networks with local frames for efficient geometric approximation.
problem Equivariance in deep learning for arbitrary transformations, especially in physics.
method Introduces SE(3) equivariant graph neural networks with complete local frames to efficiently approximate geometric quantities.
result Achieves best or competitive performance in Newton mechanics modeling and equilibrium molecule conformation generation.
A large consensus now seems to take for granted that the distributions of empirical returns of financial time series are regularly varying, with a tail exponent close to 3. We revisit this results and use standard tests as well as develop a battery of new non-parametric and parametric tests (in particular with stretche…
The so-called risk diversification principle is analyzed, showing that its convenience depends on individual characteristics of the risks involved and the dependence relationship among them. ----- Se analiza el principio de diversificación de riesgos y se demuestra que no siempre resulta mejor que no diversificar, pues…
Attention mechanism is a hot spot in deep learning field. Using channel attention model is an effective method for improving the performance of the convolutional neural network. Squeeze-and-Excitation block takes advantage of the channel dependence, selectively emphasizing the important channels and compressing the rel…
The paper optimizes stock portfolios with constraints based on performance attribution.
problem Optimizing stock portfolios with performance attribution constraints.
method Minimizes expected tail loss, constrains asset allocation and selection effect, tests on Dow Jones stocks.
result Imposing constraints on asset allocation and selection effect improves portfolio performance.
SE-KGE embeds spatial data into KGs for better spatial reasoning.
problem Spatially explicit KG embeddings for geographic tasks.
method Location-aware KG embedding model SE-KGE.
result SE-KGE outperforms baselines on DBGeo dataset.
CeCNN predicts SE and AL from UWF images, improving myopia screening.
problem Predicting axial length and spherical equivalence from UWF fundus images.
method Copula-enhanced Convolutional Neural Network (CeCNN) for multiresponse regression.
result CeCNN improves prediction of SE and AL compared to baseline CNNs.
New method improves sparse signal reconstruction using 1RSB-AMP.
problem Sparse signal reconstruction with improved accuracy.
method Developed 1RSB-AMP and 1RSB-SE for SCAD penalty minimization.
result 1RSB-AMP achieves improved reconstruction compared to RS-AMP.
Improves RLHF sample efficiency by scaling reward complexity polynomially.
problem Exponential sample complexity in RLHF algorithms for skewed preferences.
method SE-POPO, an online RLHF algorithm that achieves polynomial sample complexity.
result SE-POPO outperforms existing algorithms in sample efficiency.
Proposes HypCSE for enhanced hierarchical clustering.
problem Challenges in existing hierarchical clustering methods.
method Hyperbolic Continuous Structural Entropy (HypCSE) neural networks.
result Superior performance on seven datasets.
PenduMAV is a 6-input omnidirectional MAV without internal forces.
problem Designing a MAV without internal forces and structural costs.
method Multibody dynamics derivation, SE(3) control, Lyapunov analysis, Gazebo simulations.
result Asymptotic stabilization of the closed-loop system under parametric uncertainty and actuator noise.
Total variation regularization and total variation flows (TVF) have been widely applied for image enhancement and denoising. To include a generic preservation of crossing curvilinear structures in TVF we lift images to the homogeneous space M=Rd⋊Sd−1 of positions and orientations as a Lie group…
The paper explores metrics on Lie groups and their connections to dual quaternions.
problem Understanding metrics on Lie groups and their geometric properties.
method Analyzing Cartan-Schouten metrics on perfect Lie groups and their connections to dual quaternions.
result Biinvariant metrics on perfect Lie groups are shown to be Cartan-Schouten metrics.
Vector approximate message passing (VAMP) is a computationally simple approach to the recovery of a signal x from noisy linear measurements y=Ax+w. Like the AMP proposed by Donoho, Maleki, and Montanari in 2009, VAMP is characterized by a rigorous state evolution (SE) that holds …
GS-B3SE improves label shift estimation by smoothing priors on a graph.
problem Label shift adaptation when source and target distributions share conditional but not marginal probabilities.
method Graph-Smoothed Bayesian Black-Box Shift Estimator (GS-B3SE) places Laplacian-Gaussian priors on log-priors and confusion-matrix columns tied by a label-similarity graph. result GS-B3SE produces a tractable posterior with HMC or Newton-CG schemes, proving identifiability, contraction, and robustness.