arXiv subjects

Alexander Chang

Publications and source records attributed to Alexander Chang.

4 recordsLinked to original sources

arXiv2026

UpstreamQA: A Modular Framework for Explicit Reasoning on Video Question Answering Tasks

Video Question Answering (VideoQA) demands models that jointly reason over spatial, temporal, and linguistic cues. However, the task's inherent complexity often requires multi-step reasoning that current large multimodal models (LMMs) perform implicitly, leaving their internal decision process opaque. In contrast, large reasoning models (LRMs) explicitly generate intermediate logical steps that enhance interpretability and can improve multi-hop reasoning accuracy. Yet, these models are not designed for native video understanding, as they typically rely on static frame sampling. We propose UpstreamQA, a modular framework that disentangles and evaluates core video reasoning components through explicit upstream reasoning modules. Specifically, we employ multimodal LRMs to perform object identification and scene context generation before passing enriched reasoning traces to downstream LMMs for VideoQA. We evaluate UpstreamQA on the OpenEQA and NExTQA datasets using two LRMs (o4-mini, Gemini 2.5 Pro) and two LMMs (GPT-4o, Gemini 2.5 Flash). Our results demonstrate that introducing explicit reasoning can significantly boost performance and interpretability of downstream VideoQA, but can also lead to performance degradation when baseline performance is sufficiently high. Overall, UpstreamQA offers a principled framework for combining explicit reasoning and multimodal understanding, advancing both performance and diagnostic transparency in VideoQA in several scenarios.

cs.CV↗

arXiv2021

Cybersecurity Anomaly Detection in Adversarial Environments

The proliferation of interconnected battlefield information-sharing devices, known as the Internet of Battlefield Things (IoBT), introduced several security challenges. Inherent to the IoBT operating environment is the practice of adversarial machine learning, which attempts to circumvent machine learning models. This work examines the feasibility of cost-effective unsupervised learning and graph-based methods for anomaly detection in the network intrusion detection system setting, and also leverages an ensemble approach to supervised learning of the anomaly detection problem. We incorporate a realistic adversarial training mechanism when training supervised models to enable strong classification performance in adversarial environments. The results indicate that the unsupervised and graph-based methods were outperformed in detecting anomalies (malicious activity) by the supervised stacking ensemble method with two levels. This model consists of three different classifiers in the first level, followed by either a Naive Bayes or Decision Tree classifier for the second level. The model maintains an F1-score above 0.97 for malicious samples across all tested level two classifiers. Notably, Naive Bayes is the fastest level two classifier averaging 1.12 seconds while Decision Tree maintains the highest AUC score of 0.98.

cs.CR↗

arXiv2020

Petr4: Formal Foundations for P4 Data Planes

P4 is a domain-specific language for programming and specifying packet-processing systems. It is based on an elegant design with high-level abstractions like parsers and match-action pipelines that can be compiled to efficient implementations in software or hardware. Unfortunately, like many industrial languages, P4 has developed without a formal foundation. The P4 Language Specification is a 160-page document with a mixture of informal prose, graphical diagrams, and pseudocode. The P4 reference implementation is a complex system, running to over 40KLoC of C++ code. Clearly neither of these artifacts is suitable for formal reasoning. This paper presents a new framework, called Petr4, that puts P4 on a solid foundation. Petr4 consists of a clean-slate definitional interpreter and a calculus that models the semantics of a core fragment of P4. Throughout the specification, some aspects of program behavior are left up to targets. Our interpreter is parameterized over a target interface which collects all the target-specific behavior in the specification in a single interface. The specification makes ad-hoc restrictions on the nesting of certain program constructs in order to simplify compilation and avoid the possibility of nonterminating programs. We captured the latter intention in our core calculus by stratifying its type system, rather than imposing unnatural syntactic restrictions, and we proved that all programs in this core calculus terminate. We have validated the interpreter against a suite of over 750 tests from the P4 reference implementation, exercising our target interface with tests for different targets. We established termination for the core calculus by induction on the stratified type system. While developing Petr4, we reported dozens of bugs in the language specification and the reference implementation, many of which have been fixed.

cs.PL↗

arXiv2020

mvlearn: Multiview Machine Learning in Python

As data are generated more and more from multiple disparate sources, multiview data sets, where each sample has features in distinct views, have ballooned in recent years. However, no comprehensive package exists that enables non-specialists to use these methods easily. mvlearn is a Python library which implements the leading multiview machine learning methods. Its simple API closely follows that of scikit-learn for increased ease-of-use. The package can be installed from Python Package Index (PyPI) and the conda package manager and is released under the MIT open-source license. The documentation, detailed examples, and all releases are available at https://mvlearn.github.io/.

stat.ML↗