Farzan Farnia

Orcid: 0000-0002-6049-9232

According to our database1, Farzan Farnia authored at least 90 papers between 2013 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models.
CoRR, March, 2026

When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?
CoRR, March, 2026

Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error.
CoRR, February, 2026

PromptSplit: Revealing Prompt-Level Disagreement in Generative Models.
CoRR, February, 2026

The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning.
CoRR, February, 2026

On the Fragility of AI-Based Channel Decoders under Small Channel Perturbations.
CoRR, February, 2026

Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance.
CoRR, January, 2026

DiffResist: Physics-Constrained Diffusion for Photoresist Modeling.
Proceedings of the Design, Automation & Test in Europe Conference, 2026

FastRW: An Efficient Random Walk Method for Steady-State Thermal Analysis.
Proceedings of the Design, Automation & Test in Europe Conference, 2026

Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., December, 2025

Consistency Flow Model Achieves One-step Denoising Error Correction Codes.
CoRR, December, 2025

HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs.
CoRR, November, 2025

miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward.
CoRR, November, 2025

PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models.
CoRR, October, 2025

VirtualHAR: Virtual Sensing Device and Correlation-Based Learning Approach for Multiwearable Sensing Device-Based Human Activity Recognition.
IEEE Internet Things J., July, 2025

SPARKE: Scalable Prompt-Aware Diversity Guidance in Diffusion Models via RKE Score.
CoRR, June, 2025

Fusing Cross-modal and Uni-modal Representations: A Kronecker Product Approach.
CoRR, June, 2025

PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models.
CoRR, May, 2025

APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning.
CoRR, May, 2025

pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning.
CoRR, March, 2025

Boosting Generalization in Diffusion-Based Neural Combinatorial Solver via Energy-guided Sampling.
CoRR, February, 2025

Robust Detection of Out-of-Distribution Shifts in Chest X-ray Imaging.
J. Imaging Inform. Medicine, 2025

Do Vendi Scores Converge with Finite Samples? Truncated Vendi Score for Finite-Sample Convergence Guarantees.
Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Multilayer Matrix Factorization via Dimension-Reducing Diffusion Variational Inference.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Towards an Explainable Comparison and Alignment of Feature Embeddings.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Boosting the visual interpretability of CLIP via adversarial fine-tuning.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

On the Distributed Evaluation of Generative Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV 2025, 2025

Scendi Score: Prompt-Aware Diversity Evaluation Via Schur Complement of Clip Embeddings.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

An Information-Theoretic Approach to Diversity Evaluation of Prompt-Based Generative Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV 2025, 2025

Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024
Stability and Generalization in Free Adversarial Training.
Trans. Mach. Learn. Res., 2024

Dissecting CLIP: Decomposition with a Schur Complement-based Approach.
CoRR, 2024

Be More Diverse than the Most Diverse: Online Selection of Diverse Mixtures of Generative Models.
CoRR, 2024

On the Trade-Off between Stability and Fidelity of Gaussian-Smoothed Saliency Maps.
CoRR, 2024

Conditional Vendi Score: An Information-Theoretic Approach to Diversity Evaluation of Prompt-based Generative Models.
CoRR, 2024

On the Statistical Complexity of Estimating VENDI Scores from Empirical Data.
CoRR, 2024

Robust Model Evaluation over Large-scale Federated Networks.
CoRR, 2024

An Online Learning Approach to Prompt-based Selection of Generative Models.
CoRR, 2024

Certified Adversarial Robustness via Partition-based Randomized Smoothing.
CoRR, 2024

An Optimism-based Approach to Online Evaluation of Generative Models.
CoRR, 2024

MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations.
CoRR, 2024

On the Mode-Seeking Properties of Langevin Dynamics.
CoRR, 2024

Towards a Scalable Identification of Novel Modes in Generative Models.
CoRR, 2024

On the Inductive Biases of Demographic Parity-based Fair Learning Algorithms.
Proceedings of the Uncertainty in Artificial Intelligence, 2024

Towards a Scalable Reference-Free Evaluation of Generative Models.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

An Interpretable Evaluation of Entropy-based Novelty of Generative Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

An Information Theoretic Approach to Interaction-Grounded Learning.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provably Efficient CVaR RL in Low-rank MDPs.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

ChatPattern: Layout Pattern Customization via Natural Language.
Proceedings of the 61st ACM/IEEE Design Automation Conference, 2024

Structured Gradient-Based Interpretations via Norm-Regularized Adversarial Training.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

A Super-pixel-based Approach to the Stable Interpretation of Neural Networks.
Proceedings of the 35th British Machine Vision Conference, 2024

On Convergence in Wasserstein Distance and f-divergence Minimization Problems.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

Sparse Domain Transfer via Elastic Net Regularization.
Proceedings of the Computer Vision - ACCV 2024, 2024

2023
GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models.
SIAM J. Math. Data Sci., March, 2023

On the Evaluation of Generative Models in Distributed Learning Tasks.
CoRR, 2023

On the Role of Generalization in Transferability of Adversarial Examples.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations.
Proceedings of the IEEE International Conference on Acoustics, 2023

DiffPattern: Layout Pattern Generation via Discrete Diffusion.
Proceedings of the 60th ACM/IEEE Design Automation Conference, 2023

Mode-Seeking Divergences: Theory and Applications to GANs.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
An Optimal Transport Approach to Personalized Federated Learning.
IEEE J. Sel. Areas Inf. Theory, 2022

Universal Adversarial Directions.
CoRR, 2022

On Convergence of Gradient Descent Ascent: A Tight Local Analysis.
Proceedings of the International Conference on Machine Learning, 2022

2021
Group-Structured Adversarial Training.
CoRR, 2021

Train simultaneously, generalize better: Stability of gradient-based minimax learners.
Proceedings of the 38th International Conference on Machine Learning, 2021

A Wasserstein Minimax Framework for Mixed Linear Regression.
Proceedings of the 38th International Conference on Machine Learning, 2021

2020
Understanding GANs in the LQG Setting: Formulation, Generalization and Stability.
IEEE J. Sel. Areas Inf. Theory, 2020

A Fourier-Based Approach to Generalization and Optimization in Deep Learning.
IEEE J. Sel. Areas Inf. Theory, 2020

GANs May Have No Nash Equilibria.
CoRR, 2020

Robust Federated Learning: The Case of Affine Distribution Shifts.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Do GANs always have Nash equilibria?
Proceedings of the 37th International Conference on Machine Learning, 2020

2019
Generalizable Adversarial Training via Spectral Normalization.
Proceedings of the 7th International Conference on Learning Representations, 2019

2018
A Convex Duality Framework for GANs.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2016
A Minimax Approach to Supervised Learning.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

2015
On Feedback in Gaussian Multihop Networks.
IEEE Trans. Inf. Theory, 2015

Near Optimal Energy Control and Approximate Capacity of Energy Harvesting Communication.
IEEE J. Sel. Areas Commun., 2015

Discrete Rényi Classifiers.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Minimum HGR correlation principle: From marginals to joint distribution.
Proceedings of the IEEE International Symposium on Information Theory, 2015

2014
On feedback in Gaussian multi-hop networks.
Proceedings of the 2014 Information Theory and Applications Workshop, 2014

2013
Asymptotic behavior of network capacity under spatial network coding.
Proceedings of the 2013 IEEE Wireless Communications and Networking Conference (WCNC), 2013


  Loading...