Copertina

Spectral Superposition: A Theory of Feature Geometry

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ivanov, Georgi, Oozeer, Narmeen, Raval, Shivam, Pejovic, Tasana, Upadhyay, Shriyash, Abdullah, Amir
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Spectral Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Position: Require Frontier AI Labs To Release Small "Analog" Models
di: Upadhyay, Shriyash, et al.
Pubblicazione: (2025)

Bilinear Convolution Decomposition for Causal RL Interpretability
di: Oozeer, Narmeen, et al.
Pubblicazione: (2024)

DreamReader: An Interpretability Toolkit for Text-to-Image Models
di: Prakash, Nirmalendu, et al.
Pubblicazione: (2026)

Graph Fourier Neural Kernels (G-FuNK): Learning Solutions of Nonlinear Diffusive Parametric PDEs on Multiple Domains
di: Loeffler, Shane E., et al.
Pubblicazione: (2024)

Towards an Explainable Comparison and Alignment of Feature Embeddings
di: Jalali, Mohammad, et al.
Pubblicazione: (2025)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
di: Oozeer, Narmeen, et al.
Pubblicazione: (2025)

Perturbative adaptive importance sampling for Bayesian LOO cross-validation
di: Chang, Joshua C, et al.
Pubblicazione: (2024)

SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation
di: Kapusuzoglu, Berkcan, et al.
Pubblicazione: (2025)

Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
di: Krishnagopal, Sanjukta
Pubblicazione: (2026)

CatBOX: A Categorical-Continuous Bayesian Optimization with Spectral Mixture Kernels for Accelerated Catalysis Experiments
di: Zhao, Changquan, et al.
Pubblicazione: (2025)

Understanding and Mitigating Dataset Corruption in LLM Steering
di: Anderson, Cullen, et al.
Pubblicazione: (2026)

Angular Graph Fractional Fourier Transform: Theory and Application
di: Zhao, Feiyue, et al.
Pubblicazione: (2025)

Leave-one-out Singular Subspace Perturbation Analysis for Spectral Clustering
di: Zhang, Anderson Y., et al.
Pubblicazione: (2022)

Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices
di: Chun, Chanwoo, et al.
Pubblicazione: (2024)

Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologies
di: Parks, Ethan, et al.
Pubblicazione: (2026)

Understanding Emergent Misalignment via Feature Superposition Geometry
di: Minegishi, Gouki, et al.
Pubblicazione: (2026)

SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression
di: Nogueira, Brenda, et al.
Pubblicazione: (2025)

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
di: Roytburg, Dani, et al.
Pubblicazione: (2025)

The Positivity of the Neural Tangent Kernel
di: Carvalho, Luís, et al.
Pubblicazione: (2024)

A Spectral Approach for Learning Spatiotemporal Neural Differential Equations
di: Xia, Mingtao, et al.
Pubblicazione: (2023)

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
di: Roytburg, Dani, et al.
Pubblicazione: (2026)

Distribution-Aware Feature Selection for SAEs
di: Oozeer, Narmeen, et al.
Pubblicazione: (2025)

Complex Interpolation of Matrices with an application to Multi-Manifold Learning
di: Arbel, Adi, et al.
Pubblicazione: (2026)

Analysis and Approximate Inference of Large Random Kronecker Graphs
di: Liao, Zhenyu, et al.
Pubblicazione: (2023)

Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
di: Bianchi, Filippo Maria, et al.
Pubblicazione: (2019)

Shuffled Linear Regression via Spectral Matching
di: Liu, Hang, et al.
Pubblicazione: (2024)

A dual basis approach to multidimensional scaling
di: Lichtenberg, Samuel, et al.
Pubblicazione: (2023)

Multi-Community Spectral Clustering for Geometric Graphs
di: Allem, Luiz Emilio, et al.
Pubblicazione: (2025)

Linear probes rely on textual evidence: Results from leakage mitigation studies in language models
di: Boxo, Gerard, et al.
Pubblicazione: (2025)

How Does Attention Help? Insights from Random Matrices on Signal Recovery from Sequence Models
di: Seddik, Mohamed El Amine
Pubblicazione: (2026)

On Implications of Scaling Laws on Feature Superposition
di: Katta, Pavan
Pubblicazione: (2024)

Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
di: Prakash, Nirmalendu, et al.
Pubblicazione: (2026)

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training
di: Mohammadzadeh, Shahrad, et al.
Pubblicazione: (2024)

Approximating Human Preferences Using a Multi-Judge Learned System
di: Sprejer, Eitán, et al.
Pubblicazione: (2025)

RouterBench: A Benchmark for Multi-LLM Routing System
di: Hu, Qitian Jason, et al.
Pubblicazione: (2024)

Statistical Limits in Random Tensors with Multiple Correlated Spikes
di: Qi, Yang, et al.
Pubblicazione: (2025)

Graph Alignment via Birkhoff Relaxation
di: Varma, Sushil Mahavir, et al.
Pubblicazione: (2025)

Conformal Geometry and Spectral Bounds on Manifolds with Boundary
di: Cruz, Tiarlos, et al.
Pubblicazione: (2026)

From Data Statistics to Feature Geometry: How Correlations Shape Superposition
di: Prieto, Lucas, et al.
Pubblicazione: (2026)

Persistent Sheaf Laplacian Analysis of Protein Stability and Solubility Changes upon Mutation
di: Ren, Yiming, et al.
Pubblicazione: (2026)