论文检索

Jonathan Boel Nielsen, Xuan Huy Pham, Erdal Kayacan, Andriy Sarabakha

3D Gaussian splatting (3DGS) has recently demonstrated significant potential in computer vision, enabling high-fidelity 3D scene reconstruction with real-time rendering and fast training times. However, existing methods struggle in large, visually sparse, geometric self-similarity environments due to heavy reliance on image-based feature matching and depth information. In this work, we propose a novel reconstruction pipeline that reduces the dependence on visual features by incorporating IMU and LiDAR data to generate accurate point clouds and robustly localize images within the scene. Global colorization is achieved through 3D-to-2D projections of the localized images, which are then used to supervise 3DGS training. Our results demonstrate that the proposed pipeline significantly enhances the quality of 3D reconstruction for large, sparse scenarios, opening up new opportunities for applications in remote mapping and autonomous inspection.

Yash Bansal, Parshiv Kapoor, Agam Pandey

Large Multimodal Models (LMMs) often hallucinate objects and struggle with compositional reasoning in complex visual scenes. Structured Scene Graph (SG) representations explicitly encoding objects, attributes, and relations can mitigate these issues, however finetuning risks catastrophic forgetting. Recent zero-shot approaches prompt LMMs with scene graphs, yet typically rely on a single SG generated in one step, limiting capture of holistic context and question-specific details. We introduce a Dual-Layer Scene Graph Chain-of-Thought DLSG-CoT framework that enriches reasoning by combining two structured SGs: a Global Scene Graph (G-SG) that offers comprehensive image context, and a Query-Specific Scene Graph (Q-SG) produced through a two-step process targeting information relevant to the input query. Extensive experiments demonstrate that DLSG-CoT substantially improves LMM performance on compositional and context-sensitive tasks.

Agniva Banerjee, Arijit Sen

This paper introduces a multi-modal masked autoencoder (MMAE) that jointly denoises and classifies signals by fusing time-domain IQ sequences and constellation diagrams within a cross-attentive transformer. This approach treats noise as a learnable modality to enhance robustness, a dynamic masking curriculum combined with domain regularization training and a hybrid loss function to promote domain-invariant features. Experimentation on the RadioML 2018.01A and RadioML22 datasets demonstrates superior accuracy across different SNR levels while using substantially less labeled data than state-of-the-art approaches.

Gouranga Bala, Abhimanyu Chauhan, Amit Sethi

Reliable uncertainty quantification (UQ) is crucial for deploying deep learning models in safety-critical domains. Existing UQ methods often either rely on multi-pass inference, which increases computational cost, or restrict expressiveness by using only final-layer embeddings. In this work, we propose a lightweight evidential meta-model that leverages multi-layer feature fusion from a pretrained backbone, capturing both low-level features and high-level semantics to better estimate uncertainty. To further enhance epistemic fidelity, we integrate maximum weight-entropy (Max-WEnt) regularization, which encourages hypothesis diversity without altering the base network or adding test-time overhead. Experiments across two benchmark settings, medical (BACH, HAM10000, BreakHIS, DIV2K) and natural (ImageNet, SVHN, Fashion-MNIST, ImageNet-C) datasets, demonstrate consistent improvements in AUROC of out-of-distribution detection compared to prior post-hoc UQ methods. Our findings show that combining multi-layer evidential modeling with Max-WEnt provides a robust, efficient, and practical framework for trustworthy AI in high-stakes applications. The meta-model adds only ~0.8M parameters and trains in under four hours on a single 48GB GPU, making it practical for real-world deployment.

Jungho An, Taeyoung Kim, Haeun Kim, Dongsoo Har

Offline Zero-Shot Reinforcement Learning requires an agent to solve unseen tasks using only a fixed offline dataset without explicit rewards. A central challenge is learning representations that capture both high-level long-term planning and low-level physical dynamics. We propose a novel framework, Dynamics-Aware Planning Representation (DAPR), which disentangles these two aspects via complementary contrastive objectives. Specifically, DAPR learns goal-oriented planning directions and local dynamics-consistent directions in the latent space. By jointly enforcing these constraints, DAPR yields representations that balance “where to go” with “how to move.” Experiments on standard locomotion benchmarks (Walker, Cheetah, Quadruped) demonstrate that DAPR consistently improves performance and generalization over strong baselines, achieving substantial gains on precision demanding tasks.

Tanmay Ambadkar, Darshan Chudiwal, Greg Anderson, Abhinav Verma

Ensuring safety in deep reinforcement learning is challenging, as formal methods that provide strong guarantees often fail to scale to complex, high-dimensional systems. We introduce RAMPS, a scalable shielding framework that pairs a general-purpose, learned linear dynamics model with a robust, multi-step Control Barrier Function (CBF) for real-time safety interventions. Experiments show RAMPS significantly reduces safety violations in high-dimensional environments compared to state-of-the-art methods, without sacrificing task performance.

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.