Image de couverture de livre

Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic Interpretability

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Maitra, Kingsuk
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence 68T07, 37J06, 94A12 I.2.6; G.1.3
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Game Theoretic Free Energy Analysis of Higher Order Synergy in Attention Heads of Large Language Models
par: Bouchaffra, Djamel
Publié: (2026)

Compressive sensing inspired self-supervised single-pixel imaging
par: Lu, Jijun, et autres
Publié: (2026)

CS-SHRED: Enhancing SHRED for Robust Recovery of Spatiotemporal Dynamics
par: da Silva, Romulo B., et autres
Publié: (2025)

Probabilistic and nonlinear compressive sensing
par: Barth, Lukas Silvester, et autres
Publié: (2025)

Supervised machine learning based signal demodulation in chaotic communications
par: Kozlenko, Mykola
Publié: (2025)

The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence
par: Cai, Yichao, et autres
Publié: (2026)

Active Learning for Conditional Generative Compressed Sensing
par: DeLise, Alexander, et autres
Publié: (2026)

Multi-Hypothesis Prediction for Portfolio Optimization: A Structured Ensemble Learning Approach to Risk Diversification
par: Dominguez, Alejandro Rodriguez, et autres
Publié: (2025)

Machine Collaboration
par: Liu, Qingfeng, et autres
Publié: (2021)

CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
par: Feng, Xuchen, et autres
Publié: (2025)

RF-BayesPhysNet: A Bayesian rPPG Uncertainty Estimation Method for Complex Scenarios
par: Ma, Rufei, et autres
Publié: (2025)

Constant-Target Energy Matching: A Unified Framework for Continuous and Discrete Density Estimation
par: Zeng, Zhijun, et autres
Publié: (2026)

Machine learning based animal emotion classification using audio signals
par: Slobodian, Mariia, et autres
Publié: (2025)

A HEART for the environment: Transformer-Based Spatiotemporal Modeling for Air Quality Prediction
par: Bodendorfer, Norbert
Publié: (2025)

HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit
par: Khushiyant, et autres
Publié: (2026)

Mapping fMRI Signal and Image Stimuli in an Artificial Neural Network Latent Space: Bringing Artificial and Natural Minds Together
par: Dalbagno, Cesare Maria, et autres
Publié: (2025)

Using latent representations to link disjoint longitudinal data for mixed-effects regression
par: Schächter, Clemens, et autres
Publié: (2025)

Attribution Projection Calculus: A Novel Framework for Causal Inference in Bayesian Networks
par: Amin, M Ruhul
Publié: (2025)

Task-Synchronized Recurrent Neural Networks
par: Lukoševičius, Mantas, et autres
Publié: (2022)

Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
par: Xie, Runlong, et autres
Publié: (2026)

Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability
par: Huang, Xiaoyu, et autres
Publié: (2026)

Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption
par: Brännvall, Rickard, et autres
Publié: (2023)

Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
par: Wibbeke, Jelke, et autres
Publié: (2025)

An Artificial Intelligence-Based Framework for Predicting Emergency Department Overcrowding: Development and Evaluation Study
par: Vural, Orhun, et autres
Publié: (2025)

Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy
par: Akgul, Hasan, et autres
Publié: (2025)

Physics Informed Differentiable Solvers for Learning Parametric Solution Manifolds in Heterogeneous Physical Systems
par: Panahi, Milad, et autres
Publié: (2026)

VORT: Adaptive Power-Law Memory for NLP Transformers
par: Mlaiki, Nabil
Publié: (2026)

Deceptron: Learned Local Inverses for Fast and Stable Physics Inversion
par: Kachhadiya, Aaditya L.
Publié: (2025)

A Unified Framework for 2D Nonseparable Fractional Fourier Transform: From Geometric Completeness to Applications
par: Li, Daxiang, et autres
Publié: (2025)

Algebraic Machine Learning: Learning as computing an algebraic decomposition of a task
par: Martin-Maroto, Fernando, et autres
Publié: (2025)

A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetic
par: De Smet, Lennert, et autres
Publié: (2024)

Shallow ReLU$^s$ Networks in $L^p$-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization
par: Li, Weizhao, et autres
Publié: (2026)

Simultaneous source separation of unknown numbers of single-channel underwater acoustic signals based on deep neural networks with separator-decoder structure
par: Sun, Qinggang, et autres
Publié: (2022)

Associative Syntax and Maximal Repetitions reveal context-dependent complexity in fruit bat communication
par: Assom, Luigi
Publié: (2025)

Velocity-Inferred Hamiltonian Neural Networks: Learning Energy-Conserving Dynamics from Position-Only Data
par: Xu, Ruichen, et autres
Publié: (2025)

Ultrahigh-Q chiral resonances empowered by multi-head attention deep learning
par: Zhang, Cong, et autres
Publié: (2025)

The Non-Linearity Perturbation Threshold: Width Scaling and Landscape Bifurcations in Deep Learning
par: Alexander, Michael
Publié: (2026)

Location based Probabilistic Load Forecasting of EV Charging Sites: Deep Transfer Learning with Multi-Quantile Temporal Convolutional Network
par: Ali, Mohammad Wazed, et autres
Publié: (2024)

Deep Learning-Based Forecasting of Boarding Patient Counts to Address ED Overcrowding
par: Vural, Orhun, et autres
Publié: (2025)

IF-D: A High-Frequency, General-Purpose Inertial Foundation Dataset for Self-Supervised Learning
par: Ferreira, Patrick, et autres
Publié: (2025)