Compositional Inductive Biases for Out of Distribution Generalization
Publications
-
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
-
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
-
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
-
arXiv 2025
The Illusion of Procedural Reasoning: Measuring Long-Horizon FSM Execution in LLMs
Mohammad Mahdi Samiei, Mohammad Mansouri, Mahdieh Soleymani Baghshah
Tests long-horizon finite-state-machine execution to separate genuine procedural reasoning from shallow pattern matching.
arXiv preprint, 2025
-
arXiv 2025
VQEL: Enabling Self-Developed Symbolic Language in Agents through Vector Quantization in Emergent Language Games
Mohammad Mahdi Samiei Paqaleh, Mahdieh Soleymani Baghshah
Uses vector quantization to help interacting agents develop a discrete symbolic language in emergent communication games.
arXiv preprint, 2025