论文检索

Hyojun Ahn, Joongheon Kim

Large language models (LLMs) often generate hallucinations—fluent yet factually incorrect responses—that undermine reliability in knowledge-intensive tasks. Existing approaches for hallucination mitigation typically rely on external retrieval modules or probability heuristics, which either require additional resources or lack interpretability. In this work, we propose a diffusion-based hallucination detection framework (DHDF) that leverages U-Net denoising to reconstruct consensus answers from multiple LLM outputs. If the diffusion process exhibits spurious convergence away from factual ground truth, it provides a clear signal of hallucination. To quantify factual correctness, we incorporate TruthfulQA scores as a fact-grounded evaluation metric, distinguishing well-aligned models (high scores) from hallucination-prone models (low scores). Experimental results demonstrate that convergence dynamics under diffusion, combined with fact-grounded QA evaluation, offer an effective and interpretable pathway for hallucination detection without relying on external knowledge bases.

Mohamed Ahmed, Hyesun Choung

Traditional intercultural communication training often lacks safe spaces for open practice, leading to self-censorship and limited skill development. The ICC Tutor, an AI-powered conversational system, addresses this by offering a private, nonjudgmental environment for reflection and dialog. Using retrieval-augmented generation (RAG), the system grounds its prompts and feedback in course materials. We conducted a mixed-methods study (N = 25) with Beginner/Intermediate and expert learners. Preliminary findings suggest that the tutor helped reduce feelings of nervousness. While many beginners reported increased confidence in intercultural communication, expert learners’ confidence temporarily decreased, suggesting the AI’s role in fostering deeper self-reflection rather than just boosting perceived competence. These findings underscore the potential of AI tutors in supporting communication education and highlight the need for experience-adaptive designs to support nuanced learning trajectories.

Mrigendra Agrawal, Yunze Xiao

We present AniTales, a system designed to generate multimodal visual novels from natural language prompts. Our system integrates large language models for story generation, diffusion models for character art, and text-to-speech for voice acting. This paper describes the system's architecture and presents findings from a pilot user study. We evaluated the system with general users (n=10) and domain experts (n=5), focusing on usability, coherence, and visual consistency. General users reported high usability (SUS: 84/100) and strong character-dialogue consistency (4.2/5), along with an average score of 82/100 for their intention to continue using the platform. These initial results suggest AniTales is a promising approach for bridging the gap between text-based AI storytelling and end-to-end multimedia content creation.

Vikhyat Agarwal, Jiayi Cora Guo, Declan Hoban, Sissi Zhang, Nicholas Moran, Peter Cho, Srilakshmi Pattabiraman, Shantanu Joshi

Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model’s detection capability to new object classes requires large amounts of annotated training data, which is costly and time-consuming to acquire, especially for long-tailed classes with insufficient representation in existing datasets. We compare four distinct methods of generating synthetic data to finetune object detection models on novel object categories, particularly when limited data is available in an object-centric format (multi-view images/3D models). Our approaches are based on simple image processing techniques, 3D rendering, and image generation models, each varying in complexity and realism. We assess how our methods, which use object-centric data to synthesize realistic, cluttered images with varying contextual coherence, enable models to achieve category-level generalization in real-world data. We demonstrate significant performance boosts within this data-constrained experimental setting.

Aravinthakshan A S, Aditya Prashant Naidu, Aadiv Rath

Camouflaged object detection is critical for military, defense, and security operations, where targets evade conventional surveillance by mimicking the background or exhibiting low-contrast differences. It also supports non-invasive monitoring of elusive wildlife and endangered species, improving population estimates, habitat management, and biodiversity assessments by recovering objects that are visually indistinguishable from their surroundings. Existing solutions are computationally heavy, with large model parameters and high computational demands, which hinder deployment in real-world applications. Lightweight models have been explored, but they often compromise fine boundary fidelity. This paper introduces a lightweight Laplacian pyramid–based feature extractor that progressively aggregates multiscale Laplacian features with frequency information. The proposed architecture emphasizes object edge boundaries, enabling precise localization under subtle target–background differences while maintaining realtime efficiency. The design achieves performance comparable to the state of the art (SOTA) convolution based methods on CHAMELEON and NC4K datasets.

Yumin Zhou

Deep learning models offer state-of-the-art performance but their inherent opacity is a major barrier to adoption in high-stakes domains. In contrast, Takagi-Sugeno-Kang (TSK) fuzzy systems provide rule-based transparency but often lack the predictive power of deep networks. My PhD research addresses this critical trade-off by developing the Fuzzy-Modulated Linear Consequents (FMLC) framework, a novel hybrid architecture that synergizes these two paradigms. The core of FMLC is a deep neural network that processes fuzzified input features to generate context-dependent "modulators". These modulators dynamically parameterize a TSK-style linear consequent layer, creating a model that is both highly performant and inherently interpretable. My latest work, Learnable-FMLC (L-FMLC), advances this by introducing a regularized, adaptive fuzzification layer that autonomously learns the optimal fuzzy partitions from data, and a two-stage rule distillation framework to ensure interpretability remains scalable in high-dimensional problems. This research delivers a validated, theoretically-grounded, and scalable framework, contributing a significant step towards transparent and trustworthy AI.

Zijian Zhao

Recently, deep Reinforcement Learning (RL) methods have been widely used in labor management within transportation gig markets, such as ride-hailing, food delivery, and express delivery. Compared to traditional rule-based and optimization-based methods, RL can capture more information about long-term uncertainty and environmental dynamics, leading to better and non-myopic strategies. However, deep learning methods have long been criticized for their low interpretability, raising concerns about algorithmic discrimination in gig markets. Currently, most works focus on this issue from the perspective of statistical analysis and surveys. However, the underlying reasons related to the algorithms remain unclear, as most companies do not disclose their algorithms. This lack of transparency can hinder governments from designing efficient management policies to address these problems. To fill this research gap, this thesis proposal aims to develop appropriate RL methods to mimic the labor management behavior of transportation gig platforms and to propose effective policies that protect the rights of gig workers.

Ruihan Zhang

Machine learning is widely used in various areas. However, the current machine learning framework remains vulnerable to issues such as adversarial attacks, fairness violations, and data leakage. These problems are not adequately captured by fitting models to collected data and focusing on test performance metrics alone, like accuracy or F1-score. In practice, machine learning tasks often involve additional quantities of interest, which turns an originally unconstrained optimisation problem (only optimising toward accuracy) into a constrained one. This thesis formally studies machine learning under different types of commonly concerning constraints, such as robustness, fairness, and privacy. I first focus on how the formal machine learning framework can be extended to incorporate robustness, which is a critical factor for safety. After that, I turn to more ethics-related aspects like fairness and privacy, to explore the possibility of formally fitting them into machine learning. My approach differs from empirically pushing up multiple metrics and instead emphasises fundamental ways to understand and address the underlying challenges.

Xiliang Yang

Explainable AI (XAI) seeks to answer the question: which features of the data led a model to make its decision? Sufficient reasons are an important concept for understanding the behaviour of machine learning models, as they identify the key characteristics responsible for the prediction of an individual instance. Recent work introduced probabilistic global sufficient reasons, extending sufficient reasons from the single-instance level to all instances in the feature domain, thereby providing a global understanding of the classifier. However, prior work on this notion has been purely theoretical, without empirical evaluation. In this paper, we aim to fill this gap by developing practical methods for computing probabilistic global sufficient reasons and evaluating them on decision trees and circuit-based models.

Jian Wang

The widespread adoption of AI-assisted coding tools has fundamentally transformed software development, enabling rapid code generation but simultaneously introducing new risks to software reliability. This thesis addresses the critical challenge of ensuring trustworthy AI-assisted programming through two complementary approaches: detecting AI-generated code and advancing automated program repair. I present four major contributions: (1) The first comprehensive empirical study of AI-generated code detection across 2.24 million samples with fine-tuning-based improvements, (2) Defects4C, the first large-scale executable C/C++ bug benchmark with 248 real-world bugs, (3) Novel automated repair methods combining deep learning and LLM-based approaches with extensive empirical evaluation, and (4) A semantic enhancement framework that incorporates execution traces to improve LLM reasoning for program repair. These contributions establish new foundations for trustworthy, semantically grounded automated program repair in the era of AI-assisted development.

Fanmeng Wang

Molecular conformations, the stable three-dimensional structures corresponding to local minima on the potential energy surface, govern key molecular properties and consequently underpin a wide range of downstream tasks. However, contemporary learning-based methods often lack scalability, interpretability, and robustness, thereby significantly constraining their practical effectiveness and reliability. In this context, I will introduce my ongoing explorations and the proposed research plan to address these challenges, with the ultimate objective of developing conformation‑centric universal foundation models to accelerate scientific discovery.

Deepika SN Vemuri

This thesis aims to bridge the gap between data-driven models and symbolic learning through the lens of Concept-Based Learning, a paradigm that guides model learning through high-level, human-understandable concepts. Here, models first learn a set of concepts, subsequently using them to perform a task of interest. Prior work on concept-based models has largely focused on relatively simple classification settings, where classes are linear combinations of pre-specified concepts; treating concepts largely as tools to increase interpretability, rather than as fundamental building blocks of the learning process itself. In contrast, this thesis explores the broader potential of concepts, as the core units of representation and reasoning in neural network models, capable of shaping how models learn and generalize.

Sachin Vashistha

Large language models (LLMs) have rapidly become primary tools for searching and generating information given a carefully designed prompt (may contain few-shot examples). However, these models frequently produce factually incorrect statements that are not consistent with verifiable facts and reliable sources, raising fundamental questions about how these models store, update, and reason with facts. Improving factuality, therefore, requires more than surface-level mitigation strategies: it demands a deeper understanding of how LLMs construct and maintain world models, and how reasoning processes can be guided to remain faithful to the verifiable information. Existing strategies, such as retrieval-augmented generation, training-time alignment, post hoc verification, etc., partly address these challenges but do not provide a holistic account of how facts are internally stored, updated, or grounded in external knowledge sources. My research addresses this gap by studying factuality through the dual lens of reasoning and world modeling, asking how LLMs encode facts, how adversarial or linguistic perturbations compromise factual reasoning, and how interpretability tools can reveal and correct model vulnerabilities. In this work, I aim to develop a framework in which an LLM interacts with an explicit external knowledge source, thereby forming a robust world model for factual evaluation.

Cassandra Hui-Ming Tan

Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning, yet their efficacy is constrained by a fundamental memory limitation: a static context window that resets with each interaction. This prevents them from accumulating experience and adapting to dynamic, long-term tasks. To address the limitations of long-term memory in agentic LLMs, this work introduces a neuro-inspired framework with two key contributions. First, we propose \textbf{ARTEM} (Agentic Retrieval with Temporal-Episodic Memory), a system that organizes experiences into structured events and manages utility-based memory consolidation. Second, we extend this framework with a distinct governance component, \textbf{Value-driven ARTEM}, that validates candidate outputs against core principles before finalization. Together, these components equip LLM agents with continual learning, adaptive reasoning, and robust value-aligned decision-making. Looking forward, we outline future directions including dynamic memory adaptation, memory decay mechanisms, and applications in interactive multi-agent environments.

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.