Home Knowledge Base Differential Transformer

Differential Transformer

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster

arXiv:2605.31023v1 Announce Type: new Abstract: This work addresses the problem of autonomous resource management in heterogeneous satellite cluster conducting Earth Observation (EO) missions including optical and Synthetic Aperture Radar (SAR) satellites. In autonomous operation mode, satellites are equipped with intelligent capabilities enabling real-time decision-making based on the latest conditions, while requiring minimal interaction with ground operators. Traditional scheduling...

arXiv CS 9d ago

When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular Domains

arXiv:2605.08318v2 Announce Type: replace Abstract: We study the problem of \emph{architecture selection} for deep learning models trained to solve partial differential equations (PDEs), asking when transformer-based architectures with learned attention outperform Fourier-domain neural operators. We introduce the \textbf{Multi-Scale Attention Transformer} (\msat{}), a deep learning architecture that encodes spatiotemporal solution histories as token sequences and trains end-to-end via a...

arXiv CS 5d ago

When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular Domains

arXiv:2605.08318v2 Announce Type: replace-cross Abstract: We study the problem of \emph{architecture selection} for deep learning models trained to solve partial differential equations (PDEs), asking when transformer-based architectures with learned attention outperform Fourier-domain neural operators. We introduce the \textbf{Multi-Scale Attention Transformer} (\msat{}), a deep learning architecture that encodes spatiotemporal solution histories as token sequences and trains end-to-end via...

arXiv Physics 5d ago

Hyperspherical Variational Autoencoders Using Efficient Spherical Cauchy Distribution

arXiv:2506.21278v3 Announce Type: replace-cross Abstract: We propose spherical Cauchy (spCauchy) latent variables for variational autoencoders on hyperspherical latent spaces. The spCauchy family has heavy-tailed global behavior and admits an exact differentiable reparameterization by applying a M\"obius transformation to uniform samples on the sphere. We show that, in the high-concentration limit, spCauchy recovers the local tangent-space geometry of the von Mises-Fisher (vMF) distribution...

arXiv CS 8d ago

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs

Announce Type: new Abstract: Deep learning surrogates for 3D Partial Differential Equations (PDEs) often fail to generalize across geometric transformations because they depend heavily on specific coordinate systems. While equivariant networks offer a solution, they typically rely on local operations in the spatial domain, making the global receptive field, which is essential for PDE dynamics, computationally expensive. Conversely, Fourier Neural Operators (FNOs) efficiently capture global...

arXiv CS 7d ago

Self-focusing of helicity drives finite-time singularities in inviscid flows

arXiv:2605.17569v2 Announce Type: replace Abstract: This paper deals with the longstanding quest of the possible existence of finite-time singularities in the equations governing the dynamics of inviscid fluids, namely, Euler equations. Here, two contributions are brought for the case of perfect fluids with finite initial energy. First, a self-similar velocity field inspired by Leray Ansatz is proposed which allows for a separation of variables that transforms the original partial...

arXiv Physics 9d ago

QDAG: Declarative Composition of Reusable Analytics Methodologies at LinkedIn

arXiv:2606.05662v1 Announce Type: new Abstract: Production analytics products often depend on reusable methodologies: multi-step definitions such as headcount growth, top-skill growth, or differentially-private impression distributions. Although these methodologies define business-critical numbers, they are commonly implemented as imperative glue around OLAP queries, service calls, joins, transformations, and conditional logic. As a result, teams duplicate orchestration code, definitions...

arXiv CS 5d ago

Let There Be Light: Reflection, Refraction and Scattering for Neural Operators

arXiv:2606.03262v1 Announce Type: new Abstract: Neural operators learn mappings between infinite-dimensional function spaces and provide a data-driven surrogate modeling paradigm for parametric partial differential equations (PDEs). Existing architectures typically obtain expressivity by parameterizing integral kernels in prescribed transform domains or by applying attention-like interactions over discretized spatial points. While these approaches have achieved substantial progress, they...

arXiv CS 7d ago

TRANS: Terrain-aware Reinforcement Learning for Agile Navigation of Quadruped Robots under Social Interactions

arXiv:2602.12724v3 Announce Type: replace Abstract: This study introduces TRANS: Terrain-aware Reinforcement learning for Agile Navigation under Social interactions, a deep reinforcement learning (DRL) framework for quadrupedal social navigation over unstructured terrains. Conventional quadrupedal navigation typically separates motion planning from locomotion control, neglecting whole-body constraints and terrain awareness. On the other hand, end-to-end methods are more integrated but...

arXiv CS 8d ago

First Principles Magnetohydrodynamical Theory for the Expanding Box Model

arXiv:2606.10283v1 Announce Type: new Abstract: The Expanding Box Model (EBM) has been widely employed to simulate multiscale plasma phenomena in the expanding solar wind by transforming the MHD equations to a co-moving, non-inertial frame. However, traditional formulations have suffered from historical ambiguity regarding the physical separation between the co-moving and inertial reference frames, primarily arising from a classical approximation of an invariant magnetic field between them....

arXiv Physics 15h ago