Get started
Author

Noor Islam S. Mohammad

Observed name: Mohammad, Noor Islam S.
ORCID: 0009-0007-8823-6681
Observed ORCID: 0009-0007-8823-6681
OpenAlex ID: A5124910313
SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift
2026 · Mohammad, Noor Islam S., Shammo, Md. Basim Al Zabir, et al. · arXiv (Cornell University)
PDF
Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models
2026 · Mohammad, Noor Islam S., Bayazıt, Uluğ · arXiv (Cornell University)
PDF
The Audit Regime Gap: Regime-Conditional Bias Evaluation in Large Language Models
2026 · Noor Islam S. Mohammad
Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering
2026 · Mohammad, Noor Islam S., Bayazıt, Uluğ · arXiv (Cornell University)
PDF
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
2026 · Mohammad, Noor Islam S., Bayazit, Ulug · arXiv (Cornell University)
PDF
Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning
2026 · Mohammad, Noor Islam S., Hasan, Mahmudul · arXiv (Cornell University)
PDF
The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements
2026 · Mohammad, Noor Islam S., Sheikh, Tamim · arXiv (Cornell University)
PDF
MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions
2026 · Mohammad, Noor Islam S., Sheikh, Tamim · arXiv (Cornell University)
PDF
SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models
2026 · Mohammad, Noor Islam S., Bayazıt, Uluğ · arXiv (Cornell University)
PDF
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
2026 · Mohammad, Noor Islam S. · arXiv (Cornell University)
PDF
DSER: Spectral Epipolar Representation for Efficient Light Field Depth Estimation
2026 · Noor Islam S. Mohammad, Md Muntaqim Meherab · Preprints.org
PDF
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
2026 · Meherab, Md Muntaqim, Mohammad, Noor Islam S., et al. · arXiv (Cornell University)
PDF
Regularized Meta-Learning for Improved Generalization
2026 · Mohammad, Noor Islam S., Meherab, Md Muntaqim · arXiv (Cornell University)
PDF
Breaking the Temporal Complexity Barrier: Bucket Calculus for Parallel Machine Scheduling
2026 · Mohammad, Noor Islam S. · arXiv (Cornell University)
PDF
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
2026 · Noor Islam S. Mohammad, Ulug Bayazit · Workshop on Trustworthy NLP (TrustNLP)
PDF
Trust-Aware Multi-Axis Reliability Auditing for NLP Classifiers: A Theoretical and Empirical Framework
2026 · Noor Islam S. Mohammad
PDF
Works count: 16
Citation count:
H-index:
I10-index:
Year
Topic
Type