Zohreh Shams

7 papers · 2015–2025 · 5 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 · Silver 🏃 Academic Marathon · Half 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer

Venues

IJCAI (2) NeurIPS (2) AAAI (1) ECCV (1) ICML (1)

Top co-authors

Mateo Espinosa Zarlenga (5) Mateja Jamnik (5) Adrian Weller (3) Pietro Barbiero (3) Giuseppe Marra (1) Alice Xiang (1) Gabriele Dominici (1) Umang Bhatt (1) Swami Sankaranarayanan (1) Francesco Giannini (1)

Research topics

Artificial Intelligence (4) Deep Learning (4) Machine Learning (4) Core AI (4) Learning Types · Deep Learning (3) Application Areas (2) Architectures (2) Core Methods (2) Learning Types · Machine Learning (1)

Keywords

concept intervention (2) concept representation (2) concept bottleneck model (2) policy learning (1) explainable ai (1) model interpretability (1) concept learning (1) concept bottleneck (1) end-to-end training (1) human-ai interaction (1) human intervention (1) disentanglement learning (1) concept-based model (1) representation purity (1) test-time intervention (1) high-level concept (1) dynamic exploitation (1) leakage poisoning (1) mixcem (1) representation learning (1)

Papers

Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts ICML 2025 Efficient Bias Mitigation Without Privileged Information ECCV 2024 Learning to Receive Help: Intervention-Aware Concept Embedding Models NeurIPS 2023 Towards Robust Metrics for Concept Representation Evaluation AAAI 2023 Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off NeurIPS 2022 Normative Practical Reasoning via Argumentation and Dialogue IJCAI 2016 Normative Practical Reasoning: An Argumentation-Based Approach IJCAI 2015