Farzan Farnia

9

Papers

18

Total Citations

Papers (9)

Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach

Boosting the visual interpretability of CLIP via adversarial fine-tuning

Towards an Explainable Comparison and Alignment of Feature Embeddings

Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training

Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference

An Information Theoretic Approach to Interaction-Grounded Learning

An Interpretable Evaluation of Entropy-based Novelty of Generative Models

Scendi Score: Prompt‑Aware Diversity Evaluation via Schur Complement of CLIP Embeddings

PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models