ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Thomas Fel

Thomas Fel

1

Affiliations

Affiliations

Harvard

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 12:57 AM AMS

7

papers

309

total citations

papers (7)

CRAFT: Concept Recursive Activation FacTorization for Explainability

Don't Lie to Me! Robust and Efficient Explainability With Verified Perturbation Analysis

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit

NEURIPS 2025arXiv

Interpreting the linear structure of vision-language model embedding spaces

One Wave To Explain Them All: A Unifying Perspective On Feature Attribution