Dr. Been Kim
VERIFIED TECHNICAL DOSSIERSources checked

Dr. Been Kim

Senior Staff Research Scientist

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Dr. Been Kim. Every entry undergoes editorial source verification.

#1
RESEARCH Checked Sep 20, 2026

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Invented TCAV (Testing with Concept Activation Vectors), an interpretability framework that uses directional derivatives in activation space to quantify how much a human-understandable concept (e.g., stripes on a zebra) contributes to a model's prediction.

Model & Execution Context:InceptionV3, ResNet internal activation layers, linear classifiers in latent embedding manifolds.
Scope & Limitations

Requires user-provided exemplars for concept definitions; high-level abstract concepts without clear visual or lexical exemplars can be difficult to vectorize cleanly.

#2
RESEARCH Checked Sep 20, 2026

Relative Representations Enable Non-Degenerate Latent Space Alignment

Co-authored breakthrough research demonstrating that representations can be compared across disparate neural networks by computing pairwise angles and similarities to anchor points, proving latent geometries are invariant across architectures.

Model & Execution Context:Cross-model embedding alignment across Vision Transformers, CNNs, and language models without weight access.
Scope & Limitations

Choice and distribution of anchor points can introduce variance in representation reconstruction accuracy across domain shifts.