论文检索

Boaz Taitler

Generative AI (GenAI) has become an integral part of our lives, serving both as a tool for creating content and as a platform that interacts with users. In doing so, it not only shapes user experiences but also competes with other actors within broader economic ecosystems. This dissertation examines how GenAI interacts with users and competitors within these ecosystems. Its goal is to deepen our understanding of the implications of integrating GenAI and to design approaches that increase social welfare. The contributions include developing theoretical models of these interactions and proposing solutions through algorithmic methods, mechanism design, and regulatory frameworks that ensure welfareimproving outcomes.

Jiankai Sun

My research aims to pioneer efficient and reliable wearable intelligence algorithms that transform healthcare robotics into adaptive, patient-centered systems. I take a four-step approach: (1) design multimodal wearable sensing platforms to capture human and biometric signals; (2) train a foundation model that learns from these rich datasets to reason about human behaviors and health states; (3) validate the model through large-scale simulation and principled uncertainty quantification; and (4) deploy it in rehabilitation and assistive robots for intelligent, personalized care. This research not only advances fundamental understanding of multimodal human behavior, but also opens new pathways for early disease diagnosis, adaptive treatment, and accessible digital health. By bridging AI, wearables, and robotics, my work aspires to lay the groundwork for the next generation of healthcare technologies that are proactive, trustworthy, and deeply aligned with human well-being.

Xinwei Song

Achieving globally desirable outcomes in networked multi-agent systems—such as high social welfare, stable allocations, and widespread cooperation—is a fundamental challenge in AI. This paper outlines a research agenda that explores two complementary pathways to this goal. The first is a top-down approach, where a central mechanism designer proposes rules to guide strategic agents towards theoretically optimal equilibria. The second is a bottom-up approach, where desirable farsighted policies, like cooperation in social dilemmas, emerge from the decentralized interactions of agents via multi-agent reinforcement learning. We argue that the integration of these paths constitutes a promising frontier for creating robust and adaptive multi-agent systems.

Chang Shi

The lack of large-scale clean data for learning has been a challenge that significantly hinders robots from developing superior level of autonomous intelligence. This urges the necessity to utilize diverse data in a more efficient way. This work approaches the challenge from four perspectives: efficient learning from expert demonstration, efficient dynamics modeling from in-the-wild videos, efficient learning from heuristics guidance, and adjustment for efficient deployment. We provide an overview of preliminary results in each area and outline proposed research on extracting controllable representation from data, aiming at efficient cross-embodiment learning, as well as learning from multi fidelity data.

Hadar Shavit

Empirical performance models (EPMs) predict algorithm performance without execution, enabling applications such as algorithm selection, surrogate-based optimisation, and benchmarking. However, their effectiveness is currently constrained by the quality of feature representations and the predictive models themselves. My thesis advances EPMs by addressing both limitations. To further enhance usability and foster broader adoption, I also introduce a Python library that unifies state-of-the-art methods under a single API. These contributions aim to make EPMs more accurate, versatile, and accessible to the broader AI community.

Abdelrahman Sayed Sayed

Higher autonomy is an increasingly common goal in the design of transportation systems for the cities of the future. Recently, part of this autonomy in both rail and maritime transport has come from the field of artificial intelligence and machine learning, particularly for perception tasks (detection and recognition of rail signals, other vessels, or other elements in the vehicle environment) using neural networks. Although AI-based approaches have gained significant popularity in many application fields due to their good performance, their unpredictability and lack of formal guarantees regarding their desired behavior present a major issue for the deployment of such safety-critical systems in urban areas. The goal of my PhD thesis is to design new formal methods to analyze and ensure the safety of such AI-based perception modules in autonomous vehicles. More specifically, my PhD topic aims to formally evaluate the safety of a recently introduced class of continuous AI models which are neural ODE. Neural ODE have already been used successfully for image recognition tasks, showing higher performance compared to classical neural networks, but current work in the literature primarily focuses on their training performance, while they have been barely studied in terms of safety and formal guarantees. The main research directions that will be investigated during my PhD include: • R.D 1: Establishing formal relations between discrete and continuous neural models, and using them to deduce the safety of one model based on the safety verification of the other. • R.D 2: Analysis of the mathematical properties satisfied by the new continuous models (continuity, monotonicity, contraction, stability, etc.). • R.D 3: Exploiting these mathematical properties to study and/or enforce the overall behavior of the neural ODE with respect to various features: stability, stabilization, reachability analysis, safety, formal verification. • Verification and testing of theoretical findings on autonomous underwater vehicles (AUVs) during a 6 month mobility at the Department of Marine Technology, NTNU.

Depanshu Sani

Nature is inherently structured! The entities in the real world are naturally organized in rich relationships. For example, dolphins and sharks, despite their striking visual resemblance in body shape and fins, are actually from entirely different branches of the animal hierarchy, i.e., mammals and fishes, respectively. This remarkable similarity is a prime example of ‘convergent evolution’, where unrelated species develop similar features because they face similar environmental challenges. This illustrates how nature’s underlying organization often transcends superficial visual resemblances. Although humans intuitively grasp and utilize these profound natural constraints, they are typically underutilized in most AI systems. As a result, trained AI models tend to align with statistical patterns in the data, such as sampling biases or class imbalance, rather than adhering to the underlying relational consistency. This thesis argues that AI systems must evolve beyond learning “flat” feature representations, which are domain-agnostic and derived purely from data correlations, to “explicitly model the domain-specific structural relationships”. A key benefit of encoding relational priors in the learning process is that it can inject domain knowledge as an inductive bias, leading to more robust and reliable models. My research investigates incorporating domain knowledge by leveraging “graph-based structural priors” that explicitly model relational constraints in various visual recognition tasks. This work spans three distinct dimensions of visual recognition, progressing from coarse-level (image-level) to fine-grained (scene-level) understanding. My research highlights a crucial limitation in existing AI models: they often fail to incorporate real-world constraints, leading to significant errors. I show that even powerful, pre-trained neural networks can make severe mistakes due to a lack of domain knowledge. I argue that standard metrics like top-1 accuracy, precision, and recall are insufficient for evaluating model robustness, and propose a new metric based on rank order of the predictions as a better indicator of reliability. The benchmark on various large-scale datasets confirms that existing solutions do not sufficiently capture the domain knowledge, which is often available as a taxonomy tree, motivating our design of better learning frameworks. I also examine complex visual re-identification (Re-ID) tasks, such as monitoring animals in the wild. I find that existing foundational models struggle with new species and environments. This challenge is compounded by the high cost of manual annotation for adapting these systems to new settings. While existing unsupervised learning methods can help reduce the need for extensive labeling, they often suffer from under- and over-segmentation errors, which led me to develop more effective active learning strategies. Finally, I address the limitations of the classic Kalman filter, a widely used tool for dynamic systems. I point out that this filter makes a flawed assumption that the movement of each individual object is independent of its dynamic surroundings. In the real world, this is rarely the case. I demonstrate the need for a new filtering mechanism that not only considers an object’s past movements but also its spatial relationship with other dynamic entities in its environment. In my analysis, I observed the vision foundation models for all recognition tasks, i.e., classification, detection, and segmentation, lack the domain knowledge. I believe that our learning framework, which was designed specifically for classification, can be adapted for other recognition tasks. I speculate that a unified learning framework can be designed that can be leveraged for making vision foundation models aware of the available taxonomy.

Aniket Roy

The rapid advancement of generative models has created new opportunities for addressing core challenges in computer vision, including data scarcity, image quality, and efficient personalization. My research develops principled, resource- aware methods that enable models to generalize effectively from limited supervision, adapt efficiently to new concepts, and generate high-fidelity visual content. I first address few-shot learning through augmentation-driven uncertainty- guided mixup, improving robustness in data-constrained regimes. Building on this, I propose caption-guided multi-modal augmentation techniques that enrich visual diversity while mitigating real-to-synthetic domain gaps. To enhance the quality and realism of generated images, I introduce diffusion models grounded in natural image statistics, yielding perceptually aligned outputs suitable for downstream tasks. To advance personalization, I develop parameter-efficient mechanisms for combining low-rank adapters, enabling fine-grained control over content and style without retraining. I further extend personalization to a zero-shot setting through a training-free textual-inversion-based method that customizes arbitrary objects directly within the diffusion process. Finally, I present a frequency-guided multi-LoRA fusion framework that leverages wavelet-domain cues and timestep-aware weighting for accurate, training-free concept composition. Collectively, these contributions move toward a unified vision of generative models that are efficient, adaptive, and capable of high-quality, customizable image synthesis.

Thomas Napier

Global biodiversity is declining at unprecedented rates, yet traditional monitoring at the necessary scales remains costly and biased toward what can be seen. Sound offers a complementary lens: many species are detected more reliably by their vocalizations, microphones are inexpensive and unobtrusive, and they can cover greater spatial and temporal scales. These advantages have made passive acoustic monitoring a fast-growing paradigm, yet robust, generalizable sound distinction in complex soundscapes remain a central obstacle. My thesis addresses this by combining data-driven human-inspired representation learning with knowledge-guided unsupervised learning to prioritize hierarchical organization and structure discovery prior to labelling. Human-in-the-loop oversight is incorporated as targeted verification under uncertainty, drawing on active learning and weak supervision to direct effort where it has the highest value.

Yannis Montreuil

AI systems often fail on challenging or out-of-distribution inputs—a critical limitation in domains such as healthcare, finance, and autonomous driving. Learning to Defer (L2D) addresses this by training models not only to predict but also to decide when to defer to external experts. This thesis develops a unified and robust framework for L2D that advances its theoretical foundations, reliability, and applicability. It characterizes Bayes-optimal routing policies, establishes surrogate-consistency guarantees, and introduces a unified adversarial framework for attacking and defending L2D with Bayes-optimal robustness. It further proposes the first top-k deferral methods in both two-stage and one-stage settings. Empirical studies validate these ideas in multi-task learning and extractive question answering with large language models. Ongoing work explores token-level routing in LLMs, online adaptation with dynamic experts, and partial deferral.

Maxime Meyer

Transformers have reshaped modern artificial intelligence, yet their theoretical foundations remain incomplete. This thesis investigates the approximation power and memory limitations of transformers. I combine tools from approximation theory and statistical learning theory to provide provable guarantees on expressivity, memorization capacity, and inherent architectural constraints. My contributions include the first rigorous proof of memory bottlenecks in prompt tuning and new results on the expressivity of transformers. The long-term goal of my doctoral research is to develop a principled theoretical framework that grounds the empirical behavior of large-scale transformer models in formal approximation-theoretic results.

Connor Mattson

Learning from human feedback enables AI systems and robots to learn policies that align with human intent. While existing work has primarily examined learning from demonstrations, corrections, and preferences in single-agent settings, these ideas have yet to be fully extended to multi-agent domains—where cooperation, decentralization, and non-stationary dynamics demand new methods. In this thesis summary, I highlight my current work and outline future directions for multi-robot learning from human feedback, offering deployment strategies that align supervisor intent with robot teams in the real world.

Dongyue Lu

Autonomous driving must handle motion blur, low light, and fast-changing scenes, where RGB frames and event cameras provide complementary strengths. This thesis explores how to fuse them across the perception–reasoning–planning pipeline. It introduces FlexEvent, a frequency-robust detector with adaptive fusion and label-efficient training; Talk2Event, the first benchmark for event–language grounding with attribute-aware modeling; and the EventDrive, an event–frame VLM covering the full driving loop. Together, these contributions advance robust perception, interpretable reasoning, and reliable planning for safety-critical driving through event–frame fusion.

Samarth Khanna

My research investigates how to evaluate and enhance large language models’ (LLMs) alignment with human values in collective decision-making scenarios. I focus on three inter-related aspects of this challenge: (i) normative alignment, (ii) procedural competence, and (iii) personalization.

Jun-Peng Jiang

Tabular data is a fundamental form of information in real-world applications, ranging from finance and healthcare to scientific research. Unlike traditional views that treat tables as isolated structured data, tables are often inherently multimodal—appearing as images, embedded in documents, or coexisting with text and other modalities. My research explores multimodal tabular data learning, aiming to bridge structured tabular knowledge with diverse input forms and tasks. To this end, our work investigates leveraging tabular data as expert knowledge to provide guidance for visual modalities and enable cross-modal transfer learning. We also study more common scenarios where tables appear as images, conducting comprehensive investigations from evaluation to method development for table-based question answering and reasoning. Beyond these works, we extend tabular learning to more general scenarios, developing unified models capable of handling diverse table tasks within a single framework, and further expanding from tables to broader document-level parsing and understanding.

Tonmoy Hossain

Recent advances in deep neural networks have highlighted the importance of geometric shape in various image analysis and computer vision tasks. However, most current approaches rely on coarse or simplified shape representations, such as binary masks, meshes, or point clouds, that are primarily designed to capture global structures of objects presented in images. While effective for general image and visual understanding, these methods often fail to learn fine-grained geometric information that is critical for accurately modeling complex shapes and subtle anatomical variations. This limitation is particularly consequential in healthcare applications, where understanding fine-grained anatomical shapes and their changes is crucial for accurate disease detection and diagnosis. My research focuses on developing a set of advanced deep learning frameworks that learn robust and complex shape representations from dense image data and integrate them into the current paradigm of image appearance and texture learning.

Thi Kieu Khanh Ho

Time-series data, which represent the evolution of one or more variables over time, are ubiquitous across domains such as finance, medicine, industry, and security. Time-Series Anomaly Detection (TSAD) is essential for identifying irregular events such as equipment failures, fraudulent activities, and neurological disorders. Despite significant progress, TSAD remains challenging due to the complexity of time-series signals, the diversity of anomaly types, and the scarcity of high-quality labeled data. This thesis contributes: (i) the first comprehensive surveys of Graph-based TSAD (G-TSAD) and Self-Supervised Learning for Anomaly Detection (SSL-AD), showing how graph modeling and SSL proxy tasks yield robust representations for TSAD while mapping limits and future directions; (ii) EEG-CGS, a contrastive–generative SSL framework that encodes fine-grained subgraph structure without anomaly labels, improving multivariate TSAD and localizing anomalous sensors and regions; (iii) TSAD-C, which integrates graph representations with diffusion models to capture long-range temporal and spatial dependencies while explicitly handling contaminated training data; and (iv) extending TSAD beyond benchmark datasets into other impactful domains, and developing foundation models specialized for biosignals to detect novel anomalies in drug-resistant epilepsy patients.

Michelle Ho

Autonomous systems operating in uncertain environments without human intervention must consider several factors, including safety, reliability, and task success. State-of-the-art methods have made progress in addressing these factors individually, but often fail to unify them for deployment in real-world systems. My dissertation aims to combine methods in planning under uncertainty, failure recovery, and explainability, providing a holistic framework for comprehensive safe autonomy in real-world deployment.

Tanusree Ghosh

The rise of generative AI presents a profound duality. On one hand, it offers a powerful solution to data scarcity and privacy challenges in biometrics. On the other, it is weaponized to create deepfakes that threaten digital integrity. Existing detectors for these deepfakes are brittle, failing against real-world transformations and novel generative models. This dissertation confronts this duality head-on. First, I establish the viability of synthetic data for building fair and private biometric systems. Second, to counter the malicious use of this technology, this dissertation develops deepfake detectors designed to be robust, generalizable, and efficient by construction. My work introduces novel, lightweight feature sets on different cues (e.g., colour cue-based Relative Chrominance Difference, Gradient features, Depth cues, etc.) that are inherently resilient to OSN transformations and improve generalisation to unseen forgeries. Whereas, accomplished results confirm state-of-the-art performance, achieving high accuracy in challenging real-world scenarios with a significant reduction in model complexity, my current and future work focuses on achieving superior generalisation while being OSN manipulation resistant.

Minghong Geng

Multi-agent reinforcement learning enables sophisticated collaborative behaviors in autonomous systems, yet fundamental scalability barriers persist: existing methods struggle to coordinate large agent populations and face challenges with extended decision-making horizons. This research develops hierarchical approaches to scale up multi-agent learning systems through two complementary directions: structural scaling for coordinating increasing numbers of agents and temporal scaling for extending decision-making horizons. This paper presents four integrated contributions: a taxonomic survey establishing hierarchical architectures as the theoretical foundation for scalable multi-agent learning systems, a benchmark for long-horizon multi-objective multi-agent reinforcement learning, a framework integrating self-organizing neural networks with multiple reinforcement learning agents for hierarchical tri-level control, and a framework leveraging large language models for zero-shot multi-agent planning. Through comprehensive validation, this work demonstrates that hierarchical, heterogeneous, modular architectures provide unified, interpretable solutions to multi-agent scalability, bridging theoretical multi-agent reinforcement learning research with real-world deployment requirements.