Imagen de Portada

Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear Disentanglement

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Steier, Joshua
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Chemical Physics 68T07, 62H25, 81V55 I.2.6; J.2
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional Systems
por: MacKinlay, Dan, et al.
Publicado: (2024)

Utilizing redundancies in Qubit Hilbert Space to reduce entangling gate counts in the Unitary Vibrational Coupled-Cluster Method
por: Szczepanik, Michal, et al.
Publicado: (2024)

Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention
por: Roffo, Giorgio, et al.
Publicado: (2026)

Predicting Traffic Accident Severity with Deep Neural Networks
por: Bibb, Meghan, et al.
Publicado: (2025)

Constant-Target Energy Matching: A Unified Framework for Continuous and Discrete Density Estimation
por: Zeng, Zhijun, et al.
Publicado: (2026)

MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data
por: de Zuazo, Xabier, et al.
Publicado: (2026)

The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning
por: Rajput, Vishal
Publicado: (2026)

Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction
por: Imanov, Olaf Yunus Laitinen, et al.
Publicado: (2026)

MEDLEY-BENCH: Scale Buys Evaluation but Not Control in AI Metacognition
por: Abtahi, Farhad, et al.
Publicado: (2026)

Gradient Descent as Implicit EM in Distance-Based Neural Models
por: Oursland, Alan
Publicado: (2025)

CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
por: Feng, Xuchen, et al.
Publicado: (2025)

MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification
por: Alagöz, Celal, et al.
Publicado: (2026)

Persistent Topological Structures and Cohomological Flows as a Mathematical Framework for Brain-Inspired Representation Learning
por: Girish, Preksha, et al.
Publicado: (2025)

Unified Interaction Foundational Model (UIFM) for Predicting Complex User and System Behavior
por: Ethiraj, Vignesh, et al.
Publicado: (2025)

ProactBench: Beyond What The User Asked For
por: Harfi, Sepehr, et al.
Publicado: (2026)

A Tractography Analysis Framework Using Diffusion Maps to Study Thalamic Connectivity in Traumatic Brain Injury
por: Sharma, Akul, et al.
Publicado: (2025)

AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
por: Luo, An, et al.
Publicado: (2025)

The Price of Progress: Price Performance and the Future of AI
por: Gundlach, Hans, et al.
Publicado: (2025)

GT-PCA: Effective and Interpretable Dimensionality Reduction with General Transform-Invariant Principal Component Analysis
por: Heinrichs, Florian
Publicado: (2024)

Causal Direction from Convergence Time: Faster Training in the True Causal Direction
por: Tamim, Abdulrahman
Publicado: (2026)

Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey
por: Ballester, Rubén, et al.
Publicado: (2023)

Can Agentic AI Match the Performance of Human Data Scientists?
por: Luo, An, et al.
Publicado: (2025)

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
por: Luo, An, et al.
Publicado: (2026)

Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection
por: Chhetri, Rajeeb Thapa, et al.
Publicado: (2025)

Deriving Decoder-Free Sparse Autoencoders from First Principles
por: Oursland, Alan
Publicado: (2026)

Make Some Noise: Towards LLM audio reasoning and generation using sound tokens
por: Mehta, Shivam, et al.
Publicado: (2025)

SemAlignVC: Enhancing zero-shot timbre conversion using semantic alignment
por: Mehta, Shivam, et al.
Publicado: (2025)

Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics
por: Kumar, Pankaj, et al.
Publicado: (2025)

AGLP: A Graph Learning Perspective for Semi-supervised Domain Adaptation
por: Su, Houcheng, et al.
Publicado: (2024)

GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation
por: Wang, Mengzhu, et al.
Publicado: (2024)

DiM: $f$-Divergence Minimization Guided Sharpness-Aware Optimization for Semi-supervised Medical Image Segmentation
por: Wang, Bingli, et al.
Publicado: (2024)

A Hybrid Framework for Real-Time Data Drift and Anomaly Identification Using Hierarchical Temporal Memory and Statistical Tests
por: Bandyopadhyay, Subhadip, et al.
Publicado: (2025)

Informed deep hierarchical classification: a non-standard analysis inspired approach
por: Fiaschi, Lorenzo, et al.
Publicado: (2024)

LUCAS-MEGA: A Large-Scale Multimodal Dataset for Representation Learning in Soil-Environment Systems
por: Leng, Kuangdai, et al.
Publicado: (2026)

Simultaneously optimizing symmetry shifts and tensor factorizations for cost-efficient Fault-Tolerant Quantum Simulations of electronic Hamiltonians
por: Deka, Konrad, et al.
Publicado: (2024)

Flood Risk Follows Valleys, Not Grids: Graph Neural Networks for Flash Flood Susceptibility Mapping in Himachal Pradesh with Conformal Uncertainty Quantification
por: Sharma, Paras, et al.
Publicado: (2026)

The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
por: Wan, Shu, et al.
Publicado: (2026)

Simulating high-accuracy nuclear motion Hamiltonians using discrete variable representation and Walsh-Hadamard QROM on fault-tolerant quantum computers
por: Szczepanik, Michał, et al.
Publicado: (2025)

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis
por: Forest, Florent, et al.
Publicado: (2023)

A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
por: Ojeda, Sebastian, et al.
Publicado: (2025)