Institution profile

Fordham University

Academic institutionnorthamerica · us
Official website
Research library81linked papers
Opportunities0open roles
Selected work

Representative Papers

Causality-Aware Temporal Projection for Video Understanding in Video-LLMs

Jan 05, 2026arXiv.org

This work addresses the challenge that existing video large language models often fail to preserve strict temporal order and causal consistency due to bidirectional temporal modeling, which disrupts chronological sequence. To resolve this, the authors propose the V-CORE framework, which incorporates Learnable Spatial Aggregation (LSA) to retain spatial interactions and introduces a Causal-Aware Temporal Projector (CATP) to enforce unidirectional temporal information flow, thereby ensuring causal consistency. The approach explicitly models temporal ordering constraints through block-wise causal attention and dynamic causal sink tokens. Furthermore, it adopts 4-bit QLoRA fine-tuning with a frozen LLM backbone for computational efficiency. Evaluated on NExT-QA, the method achieves 61.2% accuracy, with notable improvements of 3.5% and 5.2% on temporal and causal reasoning subsets, respectively, demonstrating the effectiveness of the proposed temporal constraint mechanism.

1 citationsRead paper

InFusionLayer: A CFA-Based Ensemble Tool to Generate New Classifiers for Learning and Modeling

Oct 28, 2024IEEE International Conference on Tools with Artificial Intelligence

This work addresses the lack of a unified Python framework for ensemble learning methods grounded in Composite Fusion Analysis (CFA), particularly in integrating Rank-Score Characteristic (RSC) functions with Cognitive Diversity (CD). To bridge this gap, we propose InFusionLayer—a general-purpose machine learning architecture inspired by CFA that, for the first time, unifies RSC and CD mechanisms within a single framework compatible with PyTorch, TensorFlow, and Scikit-learn. Requiring only a small set of base models, our approach achieves substantial performance gains in both unsupervised and supervised multi-class classification tasks. Extensive experiments across multiple computer vision benchmarks validate its efficacy, and the open-sourced implementation facilitates the practical adoption and broader dissemination of CFA within mainstream deep learning ecosystems.

1 citationsRead paper
Recent publications

Latest Papers

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

Aug 15, 2026

This study addresses the challenges of delayed cyber incident response and unreliable recovery instructions caused by large language model hallucinations. We propose a hierarchical agent framework that integrates attack inference, reasoning-based planning, and digital twin verification. By leveraging a digital twin calibration mechanism alongside multi-agent collaboration, this approach effectively mitigates model hallucinations and enables automated decision-making. Experiments conducted on an enterprise network testbed demonstrate that our method improves recovery success rates by 18% to 31% compared to state-of-the-art LLM baselines. These results indicate a significant enhancement in the accuracy and reliability of response decisions within complex, multi-stage attack scenarios, offering a robust solution for autonomous cyber defense.

0 citationsRead paper

Contextual Value Alignment via Multilayer Combinatorial Fusion

Aug 07, 2026

This work addresses the challenge that current large language models struggle to align with human values across diverse moral contexts, as single-agent architectures and uniform reward mechanisms fail to capture ethical pluralism and the dynamics of multi-agent moral reasoning. To overcome this limitation, the authors propose a Multi-layer Compositional Fusion framework for Contextual Value Alignment (MCF-CVA), which employs multiple moral agents representing distinct value systems and integrates their outputs through an Expand-Aggregate-Reduce (EAR) iterative mechanism operating in both Euclidean score space and Kemeny ranking space. This approach uniquely combines cognitive diversity, multi-space fusion, and multi-layer iteration to achieve context-sensitive value alignment. Experimental results demonstrate that MCF-CVA significantly outperforms single-agent baselines, single-layer multi-agent methods, and existing aggregation strategies, establishing its effectiveness and robustness on standard evaluation metrics.

0 citationsRead paper