Institution profile

New Jersey Institute of Technology

Academic institutionnorthamerica · us
Official website
Research library369linked papers
Opportunities0open roles
Selected work

Representative Papers

A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

Jul 22, 2024arXiv.org

Neural architecture search (NAS) suffers from high evaluation overhead and model redundancy due to single-objective optimization (e.g., accuracy only). To address this, we propose an efficient multi-objective NAS framework. Our method introduces: (1) a novel lightweight surrogate model based on pairwise comparison that predicts relative architectural rankings instead of absolute accuracy—substantially reducing evaluation cost; and (2) a master–auxiliary dual-population co-evolutionary mechanism that enhances population diversity while ensuring convergence. Evaluated on CIFAR-10/100 and ImageNet, our approach completes search in just 0.17 GPU-days on a single GPU. On ImageNet, it discovers a compact architecture achieving 78.91% Top-1 accuracy with only 570M MAdds. Compared to state-of-the-art methods, our framework improves search efficiency by multiple orders of magnitude and significantly strengthens multi-objective optimization across accuracy, parameter count, and computational cost.

2 citationsRead paper

Watermarking Language Models with Error Correcting Codes

Jun 12, 2024arXiv.org

This work addresses the traceability of text generated by large language models (LLMs). We propose Robust Binary Coding (RBC), a watermarking framework grounded in error-correcting code theory, which losslessly embeds lightweight statistical signals into the LLM’s output token probability distribution. The method preserves text quality and human perceptibility while enabling reliable machine-generated content identification. Crucially, RBC establishes an information-theoretically modelable and statistically testable watermarking mechanism—supporting likelihood ratio tests and calibrated p-value generation. Experiments demonstrate that RBC achieves high detection accuracy, low false-positive rates, and millisecond-scale inference time across both base and instruction-tuned LLMs. Moreover, it exhibits superior robustness against common perturbations—including editing, truncation, and translation—outperforming state-of-the-art watermarking approaches.

2 citationsRead paper

Fundamental Limits of Coded Polynomial Aggregation

Jan 15, 2026

This work addresses the problem of efficiently recovering polynomial-weighted aggregation results in distributed computing systems with straggling nodes, without requiring per-term decoding. Focusing on a predetermined set of non-straggling (i.e., timely) workers, the paper proposes an aggregation framework that integrates coded computation with combinatorial design. It reveals that the intersection structure among subsets of non-straggling nodes fundamentally governs recoverability and establishes a precise threshold on the size of these intersections: when the number of such subsets is sufficiently large, this threshold becomes both necessary and sufficient for exact recovery. Moreover, the study provides an explicit coding construction that achieves recovery whenever the intersection size exceeds the threshold. Simulations demonstrate a sharp phase transition in feasibility at the threshold, confirming its tightness.

1 citations1 influentialRead paper

A Survey of Real-Time Support, Analysis, and Advancements in ROS 2

Dec 22, 2025arXiv.org

ROS 2 lacks systematic support for real-time capabilities, hindering its applicability in high-determinism robotic systems. This work presents the first comprehensive taxonomy focused on real-time performance in ROS 2, integrating multidimensional research aspects including scheduling mechanisms, communication latency modeling based on DDS, multi-threaded executor design, hardware co-design (encompassing micro-ROS and GPU real-time management), and performance profiling tools. By establishing a unified evaluation framework grounded in key metrics such as response time and data timeliness, the study systematically reviews existing approaches, clarifies the trajectory of technical evolution, and offers developers a clear optimization roadmap. The proposed framework aims to advance the ROS community’s progress toward robust real-time robotic systems.

1 citationsRead paper

A Finite Difference Approximation of Second Order Regularization of Neural-SDFs

Nov 12, 2025

To address the high computational and memory overhead of curvature regularization in neural signed distance field (SDF) learning—stemming from reliance on second-order automatic differentiation—this paper proposes a lightweight finite-difference-based regularization framework. We introduce, for the first time, an O(h²)-accurate finite-difference stencil for explicit SDF curvature modeling, bypassing Hessian construction and second-order gradients entirely. The method enables plug-and-play approximations of both Gaussian curvature and rank-deficiency loss. Empirically, it matches the reconstruction accuracy of automatic-differentiation-based curvature regularization while reducing GPU memory consumption and training time by up to 50%. Moreover, it demonstrates strong robustness to sparse, incomplete, and non-CAD data. Our core contribution is achieving high-fidelity geometric regularization at the cost of only low-order differentiation, thereby significantly improving the efficiency and scalability of neural SDF learning.

1 citationsRead paper
Recent publications

Latest Papers