DISSERTATION DEFENSE

Author : Qinyang Li

Advisor: Dr. Jianjun Hu

Date: March 18, 2026

Time: 1:20PM

Place: Online/Room 2267,  Storey Innovation Center

Remote join (ZOOM):

Link: https://sc-edu.zoom.us/j/4997546955

Abstract

The discovery and optimization of advanced materials are central to addressing global challenges in energy, healthcare, and sustainability. This dissertation develops representation-aware and distribution-aware machine learning frameworks to improve robustness, generalization, and interpretability in materials informatics and radiation detection. The work spans crystal structure mapping, adversarial learning for out-of-distribution prediction, foundation-model-based property prediction, and deep neural classification of photon interactions. A global mapping framework is first introduced to analyze the inorganic materials space using compositional, structural, physical, and neural descriptors derived from the Materials Project database. By embedding materials into low-dimensional manifolds, the framework reveals clustering behavior and structure–property relationships, enabling systematic exploration of underrepresented material families.

To address distributional fragility in materials property prediction, the Crystal Adversarial Learning (CAL) algorithm is developed. CAL synthesizes adversarial samples in high-uncertainty regions and incorporates stability-aware training objectives, improving generalization under covariate, prior, and relation shifts. Experimental results demonstrate enhanced robustness in data-scarce regimes typical of experimental materials research.

The dissertation further investigates in-context foundation models for data-efficient property prediction. By integrating a pretrained tabular transformer with compositional descriptors and graph-derived structural embeddings, the proposed framework achieves competitive performance on the MatBench benchmark suite and on lattice thermal conductivity prediction without task-specific fine-tuning. Representation analyses indicate that foundation-model adaptation reorganizes latent feature spaces to better align with physical property gradients, particularly in small-to-medium data regimes.

Finally, a deep learning framework is applied to gamma-photon interaction classification in room-temperature semiconductor detectors. The proposed model distinguishes Compton scattering and photoelectric events from pulse waveforms with high accuracy and robustness across varying noise and energy conditions, demonstrating the transferability of representation-learning principles to signal-level scientific data.

Collectively, this work advances machine learning methodologies that integrate representation geometry, distributional robustness, and physical interpretability across heterogeneous scientific domains. The developed approaches provide scalable and interpretable tools for accelerating materials discovery and improving radiation detection systems.

DISSERTATION DEFENSE

Author : Jian Liu

Advisor: Dr. Chin-Tser Huang

Date: March 17, 2026

Time: 12:30 PM

Place: Online/Room 2267,  Storey Innovation Center

Abstract

In this dissertation, we address a key reliability challenge in connected vehicle networks: V2V links can degrade sharply under adverse weather, especially in 5G mmWave channels, where environmental attenuation can be severe in regions with dust and sandstorms. Because conducting controlled field experiments in extreme weather is costly and difficult, this dissertation develops simulation-driven solutions that characterize weather-induced degradation. First, it introduces the first open-source NS-3 weather simulator for studying the adverse weather impacts on 5G mmWave V2V communications, enabling systematic evaluation under diverse environmental conditions. Building on this capability, the dissertation investigates predictive analytics such as ARIMA, Prophet, LSTM, and GRU to forecast weather-related performance degradation. We use these predictions to design a proactive channel-switching strategy that transitions from 5G mmWave to 4G LTE before major reliability loss occurs. Next, it advances beyond prediction-based control by developing a deep reinforcement learning (DRL) channel-switching approach that learns optimal switching decisions online using cumulative throughput as feedback, enabling vehicles to adapt autonomously to real-time environmental changes. Finally, this dissertation proposes a weather-aware, reinforcement learning–based open-loop power control method for decentralized sidelink V2V communication. Each vehicle learns how to adjust its transmitted power using only information it can measure locally together with the extra path loss caused by weather. In simulations from clear weather to severe rain, this approach achieves higher packet reception ratio (PRR) than the baseline 3GPP strategy and existing open-loop power control methods.

DISSERTATION DEFENSE
Department of Computer Science and Engineering

Author : Kausik Lakkaraju
Advisor: Dr. Biplav Srivastava
Date: Feb 4th, 2026
Time: 9:30 am
Place: Room 529,  AI Institute

Abstract

This dissertation examines how to assess and rate instability and bias in black-box AI models, with particular attention to large language models (LLMs) and composite AI models used in finance, healthcare, and other decision-sensitive contexts. Prior studies show that small changes in input or protected attributes (sensitive user information) can cause large shifts in model outputs, an issue that becomes more pronounced when multiple models are chained together to form a composite AI model.

The work introduces a causality-based rating method that tests black-box models to quantify sensitivity, statistical bias, and confounding effects under controlled input variations. Beyond measurement, the rating method converts raw metric scores into comparable ratings that aid users in model selection, provide holistic explanations when used in conjunction with traditional explanation methods to cater to the needs of multiple stakeholders, and support the assessment and construction of robust and efficient composite AI models when integrated with probabilistic planning methods. The rating method helps users make trade-offs among fairness, utility, and computational cost when choosing a model for a task based on the data in hand.

To support practical adoption, the dissertation presents ARC (AI Rating through Causality), a tool that applies the method across multiple tasks, supports Pareto analysis, and allows users to evaluate their own models within a fixed causal setup. User studies show that ratings reduce the effort required to understand model behavior and help users build efficient composite chatbots. This work also underpins a forthcoming Springer Nature book, Assessing, Explaining, and Rating AI Systems for Trust, With Applications in Finance.

Join us for a free event, AIx: Safe AI for Seniors on 14th November, 2025 (Friday). The event will feature panels with leading academics, professionals, and community members, on AI, cybersecurity, law and public health; open discussions on AI and what it means for seniors, AI demos, games, and lunch! More information and RSVP here.

DISSERTATION DEFENSE

Author : Xiangyu Hu
Advisor: Dr. Yan Tong
Date: Oct 24th, 2025
Time: 12:30 pm
Place: Teams
Link: https://teams.microsoft.com/l/meetup-join/19%3ameeting_Zjk5ZGM3NzctMzZm…

Abstract

With the rapid progress of deep learning, Facial Expression Recognition (FER) has seen substantial improvements in performance, particularly “in the wild” meaning real world conditions. Despite these advances, most existing methods extract features from facial images as the sole emotional cues, which limits the model’s ability to capture the full complexity of human emotional expressions.

In reality, facial expressions are composed of diverse and multi-perspective information, including appearance-based cues and geometric structural deformations due to activations of facial muscles. Depending exclusively on one type of representation may fail to exploit the complementary nature of these cues, an issue that becomes especially pronounced under real-world conditions involving poor image quality, occlusion, varying head poses, and diverse personal attributes.

To overcome this limitation, we investigate how multiple perspectives of information, such as multiple levels of semantic patterns, facial geometry captured in facial landmarks, and multimodal representation of facial expressions, can be effectively extracted from the same facial image and integrated to enrich expression-discriminative feature representations. This multi-perspective feature learning strategy not only provides a holistic interpretation of facial expressions, but also encourages the learning of robust, multi-level representations that enhance generalization.

Motivated by this, we introduce three novel models designed to extract and fuse complementary features across different representations from facial images, thereby improving both the accuracy and robustness of FER systems.

First, we propose a Cascaded Feature Fusion Network (CFFN) that leverages low-level semantic features to refine predictions typically dominated by high-level semantic information. CFFN utilizes a multi-branch architecture featuring Semantic Feature Fusion Blocks (SFFB) to enable effective communication between neighboring branches. Additionally, Multi-Branch Fusion Blocks (MBFB) integrate multi-scale semantic features, facilitating predictions from multilevel features. Experimental results demonstrate that the proposed model achieves state-of-the-art performance, with further cross-dataset evaluations highlighting its generalization capability.

Secondly, we propose a Context-Aware Multi-cue Model (CAMM) to enhance FER by jointly leveraging appearance, geometric, and semantic information. The framework utilizes two coordinated CNN backbones to extract complementary facial appearance and geometry features; while a pretrained vision–language model generates descriptive captions that are encoded into semantic embeddings. These embeddings are incorporated into both visual branches through a Text Fusion Block (TFB) built upon Adaptive Instance Normalization, enabling adaptive modulation of visual representations guided by global semantic context. In addition, a Weighted Dilated Block (WDB) is introduced to aggregate multi-scale spatial information with learnable attention weights, thereby enhancing contextual perception. By aligning high-level semantics with spatial structure and visual appearance, CAMM produces robust and discriminative representations, achieving state-of-the-art performance under real-world conditions.

Third, we introduce a Semantic-Consensus Multi-Modal Learning (SC-MML) framework to address the challenge of noisy labels in in-the-wild FER datasets. SC-MML incorporates high-level textual descriptions generated by a pretrained vision–language model as an auxiliary modality, providing robust semantic cues that capture nuanced facial attributes and contextual emotion. The framework comprises two coordinated components: a Consensus Branch that constructs noise-robust soft labels by aggregating mutual nearest neighbors across visual and textual embedding spaces, and a Discriminative Branch equipped with a Query-Guided Gated Fusion (QGGF) module. The QGGF adaptively fuses semantic and visual representations through a gating mechanism that highlights consistent and informative cues while suppressing noisy or redundant information. By grounding supervision in cross-modal semantic consensus rather than potentially corrupted categorical annotations, SC-MML effectively decouples learning from noisy labels and enhances representation reliability. This consensus-driven design strengthens the robustness to annotation noise and improves generalization in complex real-world scenarios. Extensive evaluations on multiple benchmark FER datasets demonstrate that SC-MML surpasses existing noise-robust methods, offering a principled and efficient paradigm for multimodal learning under noisy supervision.

DISSERTATION DEFENSE

Author : Rabins Wosti
Advisor: Dr. Stephen Fenner
Date: Oct 17th, 2025
Time: 3:00 pm
Place: Room 2265 Innovation Building

Abstract

The accurate computation of advanced quantum algorithms like Shor’s integer factorization, quantum phase estimation (QPE), and the quantum Fourier transform (QFT) requires quantum circuits of considerable size and depth. It is difficult to achieve reliable computation with deep quantum circuits due to the limited coherence times of the current noisy quantum devices. The quantum fanout gate is known to be a powerful primitive for reducing the depth of many quantum circuits (Høyer and Špalek 2003; Gottesman and Isaac L. Chuang 1999). Shallow or constant-depth quantum circuits are desirable for both near-term and fault-tolerant quantum computations as they reduce noise and allow faster execution of quantum algorithms, potentially skirting the effects of short coherence times. In this work, we show new approaches towards implementation of quantum fanout gate. In particular, we show that by analogously time-evolving the quantum systems according to two well-studied Hamiltonians, namely quantum Ising and quantum Heisenberg models, we can implement quantum fanout operator using constant additional layers of digital quantum gates.

Important foundations to the area of quantum encoding were provided by Schumacher who proved the quantum analog of Shannon’s noiseless coding theorem for an independent and identically distributed (i.i.d.) quantum source, (Schumacher 1995). In this work, we show a lossless, variable-length block encoding scheme of quantum information emitted from a completely general stochastic quantum source, and it is encoded into the Fock space. While doing so, we extend the notion of uniquely de- codable (or completely lossless) quantum codes to be used for quantum block data compression. As our main result, for a fixed ml many pure states emitted by a given quantum stochastic source, we derive the optimal lower bound of the average codeword length over a subset of uniquely decodable quantum codes called “special block codes”, which are applied to encode the pure states of m many blocks each of block size l. Additionally, we show that for quantum stationary sources in particular, the optimal lower bound of the average codeword length per symbol computed over a subset of special block codes called “constrained special block codes” equals the von-Neumann entropy rate of the source for an asymptotically long block size.

DISSERTATION DFENSE
 

Author : Amarakoon Mudiyanselage Thilini Ishanka Wijesiriwardene
Advisor: Dr. Amit Sheth
Date: Oct 16th, 2025
Time: 10:00 am
Place: AI Institute Seminar room
Join Zoom Meeting: https://sc-edu.zoom.us/j/86209851277?pwd=frrKtfwOKKs4EHZWkly1pfahO0z7n6…
Meeting ID: 862 0985 1277
Passcode: 309819

Abstract

Analogy-making is central to human cognition, requiring the integration of abstract reasoning, pattern recognition, and background knowledge. Despite significant advances in language modeling, the capacity of current methods to accurately identify, model, and evaluate analogies remains fundamentally underexplored.

Analogies are central to human cognition, enabling individuals to perceive deep similarities between superficially different situations. Effective analogy-making requires integrating knowledge about the external world with abstract reasoning and pattern recognition capabilities. While current language models (LMs), trained on massive textual corpora using autoregressive or masked objectives, achieve impressive performance across Natural Language Processing (NLP) tasks such as text generation, summarization, and classification, their capacity for analogical reasoning remains poorly understood. Three factors contribute to this gap: the inherent complexity of analogy-making, the scarcity of suitable evaluation data, and the absence of systematic frameworks for quantifying analogy complexity. This dissertation bridges this gap by advancing both the theoretical understanding of analogies in LMs and the practical tools needed to benchmark and improve their analogical capabilities.

This work makes six interconnected contributions to computational analogy research. First, we introduce a complexity-grounded taxonomy of analogies and develop evaluation methods that assess Large Language Models (LLMs) across this spectrum, revealing that knowledge-enhanced approaches are essential for proportional and long-text analogies. Second, we analyze student-generated analogies in Biochemistry, demonstrating how both hand-engineered features and LLM-generated embeddings contribute to distinguishing strong from weak analogies in educational contexts. Third, through linguistic probing techniques, we investigate the relationship between LLMs' syntactic-semantic encoding capabilities and their performance on sentence-level analogies. Fourth, we propose knowledge-enhanced methods specifically designed to address the challenging proportional analogies identified in our taxonomy. Fifth, we develop a generation pipeline for realistic long-text analogies addressing the limitations of existing overly-clean datasets, and benchmark state-of-the-art LLMs while exploring Graph Neural Network-based complementary evaluation methods. Sixth, recognizing that analogy research requires distinguishing between related phenomena of abstraction, we present a systematic taxonomy of abstraction levels, addressing the lack of consistent operational definitions in the Computer Science literature.

Together, these contributions establish a comprehensive framework for understanding, evaluating, and improving analogical reasoning in the era of large language models, with implications for both cognitive modeling and practical NLP applications.

 DISSERTATION DFENSE
 

Author : Md Hasibul Amin
Advisor: Dr. Ramtin Zand
Date: Sep 24th, 2025
Time: 2:00 pm
Place: Teams Meeting

Abstract

There has been a rapid growth in the computational demands of machine learning (ML) workloads in recent days. Conventional von Neumann architectures are not capable of keeping up with the high cost of data movement between the processor and memory, well-known as memory wall problem. In-memory computing (IMC) has been focused as a solution by the researchers, where the computation is performed inside the memory devices such as SRAM, MRAM, RRAM etc. Most commonly, the memory devices are arranged in a crossbar setting where the matrix-vector multiplication (MVM) operation is performed through intrinsic parallelism of analog computations. The conventional IMC systems require high-power signal conversion blocks to connect between analog crossbars and digital processing units, hindering efficient computation. In this dissertation, we propose In-Memory Analog Computing (IMAC) architectures that perform the MVM and nonlinear vector operation (NLV) consequently using analog functional units, eliminating the needs for costly signal conversions. Despite its advantages, computing the whole DNN in the analog domain introduces critical usability and reliability challenges. This dissertation systematically investigates these challenges and presents a set of circuit-, system-, and architecture-level solutions to mitigate their impact. Furthermore, we develop a comprehensive simulation framework to enable cross-layer design and performance optimization of IMAC systems tailored to user-defined ML workloads. Our results demonstrate that IMAC can achieve significant energy and latency savings with negligible accuracy loss, making it a compelling direction for next-generation ML hardware acceleration.

DISSERTATION DFENSE
Department of Computer Science and Engineering

Author : Alireza Bagheri Rajeoni
Advisor: Dr. Homayoun Valafar
Date: Sep 24th, 2025
Time: 11:00 am
Place: Rm 2267, Storey Innovation Building

Abstract

The analysis of vascular structures is critical for diagnosing, monitoring, and treating cardiovascular diseases such as aneurysms, stenosis, and vascular calcification. Traditional methods often rely on manual interpretation of imaging data, which is time-consuming, subjective, and not scalable. This work explores the application of machine learning techniques to automate and enhance vascular system analysis across multiple research efforts. Leveraging both supervised and unsupervised learning, the studies presented encompass tasks such as vessel segmentation, anomaly detection, boundary localization, calcium measurement, and volume estimation from computed tomography angiography (CTA) data. Emphasis is placed on overcoming challenges in data scarcity through the use of pre-trained models, transfer learning, and rule-based systems. Results demonstrate that machine learning, when carefully integrated with domain knowledge, can deliver accurate, interpretable, and scalable tools for vascular assessment. This compilation highlights the potential of AI-driven methods to support clinical decision-making and improve vascular diagnostics in real-world settings.