Istanbul Technical University

university

Verified

https://itu.edu.tr/en/

AI & ML interests

Machine learning, deep learning, computer vision, artificial intelligence, natural language processing, and large language models are key areas of modern intelligent systems.

Recent Activity

nislamsm authored a paper 19 days ago

SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift

nislamsm authored a paper 29 days ago

Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models

nislamsm authored a paper 29 days ago

CORE-STACK+: Meta-Learning for Deep Stacked Generalization

View all activity

Papers

SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

View all Papers

authored a paper 19 days ago

SIFT: Robust Meta-Faithfulness Verification of Chain-of-Thought Reasoning Under Distribution Shift

Paper • 2610.04594 • Published 25 days ago

authored 3 papers 29 days ago

Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models

Paper • 2609.13534 • Published Sep 11

CORE-STACK+: Meta-Learning for Deep Stacked Generalization

Paper • 2609.26905 • Published Sep 22

Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering

Paper • 2607.25422 • Published Jul 28

authored 4 papers 4 months ago

SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization

Paper • 2606.24259 • Published Jun 23

Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning

Paper • 2606.21083 • Published Jun 19

MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions

Paper • 2606.16562 • Published Jun 15

The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements

Paper • 2606.16541 • Published Jun 15

authored a paper 6 months ago

SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

Paper • 2604.16606 • Published Apr 17

submitted a paper to Daily Papers 6 months ago

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

Paper • 2604.14663 • Published Apr 16 • 3

authored a paper 6 months ago

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

Paper • 2604.14663 • Published Apr 16 • 3

updated a Space 6 months ago

Istanbul Technical University (ITU)

İTÜ — Engineering & AI research university, Istanbul

published a Space 6 months ago

Istanbul Technical University (ITU)

İTÜ — Engineering & AI research university, Istanbul

authored a paper 8 months ago

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning

Paper • 2603.10377 • Published Mar 11 • 3

submitted a paper to Daily Papers 8 months ago

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning

Paper • 2603.10377 • Published Mar 11 • 3

authored 2 papers 8 months ago

Regularized Meta-Learning for Improved Generalization

Paper • 2602.12469 • Published Apr 23

Breaking the Temporal Complexity Barrier: Bucket Calculus for Parallel Machine Scheduling

Paper • 2602.01356 • Published Feb 1

authored 3 papers about 1 year ago

CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification

Paper • 2510.17018 • Published Apr 7 • 1

Reveal-to-Revise: Explainable Bias-Aware Generative Modeling with Multimodal Attention

Paper • 2510.12957 • Published Apr 7

Hierarchical Spatial Algorithms for High-Resolution Image Quantization and Feature Extraction

Paper • 2510.08449 • Published Oct 9, 2025