3 papers
cs.LG2026
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Md Muntaqim Meherab, Noor Islam S. Mohammad, Faiza Feroz
Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed a…
cs.LG2026
Regularized Meta-Learning for Improved Generalization
Noor Islam S. Mohammad, Md Muntaqim Meherab
Deep ensemble methods often improve predictive performance, yet they suffer from three practical limitations: redundancy among base models that inflates computational cost and degr…
cs.CV2026
DSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation
Noor Islam S. Mohammad, Md Muntaqim Meherab
Dense light field depth estimation remains challenging due to sparse angular sampling, occlusion boundaries, textureless regions, and the cost of exhaustive multi-view matching. We…