Cover Image

When Attention Collapses: Residual Evidence Modeling for Compositional Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Houba, Niklas
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Data Analysis, Statistics and Probability
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bayesian Inference with Deep Weakly Nonlinear Networks
by: Hanin, Boris, et al.
Published: (2024)

Practically Effective Adjustment Variable Selection in Causal Inference
by: Noda, Atsushi, et al.
Published: (2025)

Neural Thermodynamic Laws for Large Language Model Training
by: Liu, Ziming, et al.
Published: (2025)

A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification
by: Corradini, Flavio, et al.
Published: (2024)

PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
by: Miao, Tingjia, et al.
Published: (2026)

Superposition unifies power-law training dynamics
by: Chen, Zixin Jessie, et al.
Published: (2026)

The most likely common cause
by: Hovhannisyan, A., et al.
Published: (2023)

Optimal Symmetries in Binary Classification
by: Ngairangbam, Vishal S., et al.
Published: (2024)

Physics of Skill Learning
by: Liu, Ziming, et al.
Published: (2025)

Nonnegative matrix factorization and the principle of the common cause
by: Khalafyan, E., et al.
Published: (2025)

Uncertainty Quantification with Bayesian Higher Order ReLU KANs
by: Giroux, James, et al.
Published: (2024)

On the continuity of flows
by: Sha, Congzhou M
Published: (2025)

DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design
by: Yu, Xinling, et al.
Published: (2025)

A Neural Scaling Law from Lottery Ticket Ensembling
by: Liu, Ziming, et al.
Published: (2023)

Mesh-free sparse identification of nonlinear dynamics
by: Gao, Mars Liyao, et al.
Published: (2025)

Toward Dynamic Stability Assessment of Power Grid Topologies using Graph Neural Networks
by: Nauck, Christian, et al.
Published: (2022)

Deep source separation of overlapping gravitational-wave signals and non-stationary noise artifacts
by: Houba, Niklas
Published: (2025)

Anomaly Detection in Soil Heavy Metal Contamination Using Unsupervised Learning for Environmental Risk Assessment
by: Adjokatse, Isaac Tettey, et al.
Published: (2026)

Deep Learning Domain Adaptation to Understand Physico-Chemical Processes from Fluorescence Spectroscopy Small Datasets: Application to Ageing of Olive Oil
by: Michelucci, Umberto, et al.
Published: (2024)

SlotFlow: Amortized Trans-Dimensional Inference with Slot-Based Normalizing Flows
by: Houba, Niklas, et al.
Published: (2025)

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)
by: Nam, Yoonsoo, et al.
Published: (2025)

Smart Ensemble Learning Framework for Predicting Groundwater Heavy Metal Pollution
by: Ansah-Narh, T., et al.
Published: (2026)

PRISM: Deriving a White-Box Transformer as a Signal-Noise Decomposition Operator via Maximum Coding Rate Reduction
by: Huang, Dongchen
Published: (2026)

PATHFINDER: Multi-objective discovery in structural and spectral spaces
by: Barakati, Kamyar, et al.
Published: (2026)

PIED: Physics-Informed Experimental Design for Inverse Problems
by: Hemachandra, Apivich, et al.
Published: (2025)

PINNACLE: PINN Adaptive ColLocation and Experimental points selection
by: Lau, Gregory Kang Ruey, et al.
Published: (2024)

Adaptive Behavioral AI: Reinforcement Learning to Enhance Pharmacy Services
by: del Río, Ana Fernández, et al.
Published: (2024)

Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play
by: Ye, Ziyu, et al.
Published: (2024)

Understanding complex crowd dynamics with generative neural simulators
by: Minartz, Koen, et al.
Published: (2024)

The role of data embedding in quantum autoencoders for improved anomaly detection
by: Araz, Jack Y., et al.
Published: (2024)

KAN 2.0: Kolmogorov-Arnold Networks Meet Science
by: Liu, Ziming, et al.
Published: (2024)

Free Energy Risk Metrics for Systemically Safe AI: Gatekeeping Multi-Agent Study
by: Walters, Michael, et al.
Published: (2025)

Stochastic Clock Attention for Aligning Continuous and Ordered Sequences
by: Soh, Hyungjoon, et al.
Published: (2025)

Global Tropical Cyclone Intensity Forecasting with Multi-modal Multi-scale Causal Autoregressive Model
by: Wang, Xinyu, et al.
Published: (2024)

Probabilistic Emissivity Retrieval from Hyperspectral Data via Physics-Guided Variational Inference
by: Tempelman, Joshua R., et al.
Published: (2025)

Stochastic Inference of Plate Bending from Heterogeneous Data: Physics-informed Gaussian Processes via Kirchhoff-Love Theory
by: Kavrakov, Igor, et al.
Published: (2024)

Developing Machine Learning-Based Watch-to-Warning Severe Weather Guidance from the Warn-on-Forecast System
by: Flora, Montgomery, et al.
Published: (2026)

Bayesian Inference of Minimally Complex Models with Interactions of Arbitrary Order
by: de Mulatier, Clélia, et al.
Published: (2020)

Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
by: Brenner, Manuel, et al.
Published: (2024)

Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
by: Zheng, Candi, et al.
Published: (2023)