Out-of-Distribution Generalization
Building models that generalize beyond training distributions.
Robustness to Spurious Correlation
We develop frameworks that mitigate shortcut learning and improve robustness under subpopulation shifts, including realistic settings where spurious correlations are unknown or unlabeled.
Language-Informed Reinforcement Learning
We study how language abstractions and compositional representations can guide agents toward robust performance in unseen environments.
Compositional and Complex OoD
We create benchmarks and learning methods for shifts formed by novel compositions of previously seen concepts.
Publications
-
ICLR 2026
Implicit Regularization of SGD Reduces Shortcut Learning
Nahal Mirzaie, Alireza Alipanah, Ali Abbasi, Amirmahdi Farzane, Hossein Jafarinia, Erfan Sobhaei, Mahdi Ghaznavi, Amir Najafi, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Shows how the implicit regularization of SGD, controlled by learning rate and batch size, suppresses reliance on spurious features while preserving accuracy.
International Conference on Learning Representations (ICLR), 2026
-
TMLR 2026
Bridging Reasoning to Learning: Unmasking Illusions Using Complexity Out-of-Distribution Generalization
Mahdi Samiei, Arash Marioriyad, Arman Tahmasebi-Zadeh, Mohamadreza Fereydooni, Mahdi Ghaznavi, Mahdieh Soleymani Baghshah
Frames reasoning as generalization to problems whose solutions require greater representational or computational complexity than the training examples.
Transactions on Machine Learning Research (TMLR), 2026
-
NeurIPS 2025
Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
Reihaneh Zohrabi, Hosein Hasani, Mahdieh Soleymani Baghshah, Anna Rohrbach, Marcus Rohrbach, Mohammad Hossein Rohban
Refines class prototypes with explicit awareness of spurious features to make out-of-distribution detection more reliable under shortcut-driven shifts.
Advances in Neural Information Processing Systems (NeurIPS), 2025
-
Machine Learning 2025
Inductive Biases for Zero-Shot Systematic Generalization in Language-Informed Reinforcement Learning
Negin Hashemi Dijujin, Seyed Roozbeh Razavi Rohani, Mohammad Mahdi Samiei, Mahdieh Soleymani Baghshah
Studies compositional inductive biases that help language-informed reinforcement learning agents generalize systematically to unseen task combinations.
Machine Learning (Springer), 2025
-
TMLR 2025
CAREL: Instruction-Guided Reinforcement Learning with Cross-Modal Auxiliary Objectives
Armin Saghafian, Amirmohammad Izadi, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah
Uses cross-modal auxiliary objectives and instruction tracking to improve sample efficiency and systematic generalization in language-guided reinforcement learning.
Transactions on Machine Learning Research (TMLR), 2025
-
2025 Position paper
Position: System-2 AI Is About Complexity Out of Distribution
Mohammad Mahdi Samiei, Mohamadreza Fereydooni, Yaser Javaherian, Mahdieh Soleymani Baghshah
Argues that System-2 behavior is best understood as generalization beyond the computational complexity represented in training examples.
Position paper, 2025
-
ICML HiLD 2025
The Silent Helper: How Implicit Regularization Enhances Group Robustness
Nahal Mirzaie, Mahdi Ghaznavi, Hamed Oyarhoseini, Alireza Alipanah, Erfan Sobhaei, Ali Abbasi, Mahdieh Soleymani Baghshah
Studies how the implicit bias of optimization can improve worst-group performance even when group annotations are unavailable.
ICML Workshop on High-dimensional Learning Dynamics (HiLD), 2025
-
ICLR SCSL 2025
Exploiting What Trained Models Learn for Making Them Robust to Spurious Correlations without Group Annotations
Mahdi Ghaznavi, Hadi Asadollahzadeh, Fahimeh Hosseini Noohdani, Soroush Vafaie Tabar, Hosein Hasani, Mahdieh Soleymani Baghshah
Uses information already encoded by trained models to reduce shortcut reliance without requiring group labels during training.
ICLR Workshop on Spurious Correlation and Shortcut Learning (SCSL), 2025