Arshia Soltani Moakhar

4 papers · 2022–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 👥 Mega-Team · Legion

Venues

ICML (2) ICLR (1) NeurIPS (1)

Top co-authors

Mohammad Azizmalayeri (2) Mohammad Hossein Rohban (2) Michael Chang (1) Mohamed A. Haggag (1) Hamid Reza Dehbashi (1) Joel Niklaus (1) Maral Jabbarishiviari (1) Sepehr Ghobadi (1) Micol Altomare (1) Swati Rajwal (1)

Research topics

Artificial Intelligence (4) Deep Learning (3) Core AI (3) Machine Learning (2) Learning Types · Machine Learning (2) Natural Language Processing (1) Architectures (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Models (1) Resources & Methods (1)

Keywords

benchmark evaluation (1) question answering (1) adversarial training (1) outlier detection (1) sparsity (1) saliency map (1) adversarial setting (1) adversarial attack (1) out-of-distribution detection (1) text-to-image model (1) adversarial example (1) multilingual language model (1) language gap (1) regional knowledge (1) neuron visualization (1) adversarially trained discriminator (1) pre-processing (1) pruning (1) diverse outliers (1) near-distribution outliers (1)

Papers

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge ICLR 2025 RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples ICML 2024 SPADE: Sparsity-Guided Debugging for Deep Neural Networks ICML 2024 Your Out-of-Distribution Detection Method is Not Robust! NeurIPS 2022