Crime situations are race against time. An AI-assisted criminal investigation system, providing prompt but precise legal counsel is in need for police officers. We introduce LAPIS (Language Model Augmented Police Investigation System), an automated system that assists police officers to perform rational and legal investigative actions. We constructed a finetuning dataset and retrieval knowledgebase specialized in crime investigation legal reasoning task. We extended the dataset's quality by incorporating manual curation efforts done by a group of domain experts. We then finetuned the pretrained weights of a smaller Korean language model to the newly constructed dataset and integrated it with the crime investigation knowledgebase retrieval approach. Experimental results show LAPIS' potential in providing reliable legal guidance for police officers, even better than the proprietary GPT-4 model. Qualitative analysis on the rationales generated by LAPIS demonstrate the model's reasoning ability to leverage the premises and derive legally correct conclusions.

Despite the successes and progress of deep reinforcement learning over the last decade, several challenges remain that hinder its broader application. Some fundamental aspects to improve include data efficiency, generalization capability, and ability to learn in sparse-reward environments, which often require human-designed dense rewards. Meta-learning has emerged as a promising approach to address these issues by optimizing components of the learning algorithm to meet desired characteristics. Additionally, a different line of work has extensively studied the use of intrinsic rewards to enhance the exploration capabilities of algorithms. This work investigates how meta-learning can improve the training signal received by RL agents. The focus is on meta-learning intrinsic rewards under a framework that doesn't rely on the use of meta-gradients. We analyze and compare this approach to the use of extrinsic rewards and a meta-learned advantage function. The developed algorithms are evaluated on distributions of continuous control tasks with both parametric and non-parametric variations, and with only sparse rewards accessible for the evaluation tasks.

This study introduces a taxonomy of stereotype content in contemporary large language models (LLMs). We prompt ChatGPT 3.5, Llama 3, and Mixtral 8x7B, three powerful and widely used LLMs, for the characteristics associated with 87 social categories (e.g., gender, race, occupations). We identify 14 stereotype dimensions (e.g., Morality, Ability, Health, Beliefs, Emotions), accounting for ~90% of LLM stereotype associations. Warmth and Competence facets were the most frequent content, but all other dimensions were significantly prevalent. Stereotypes were more positive in LLMs (vs. humans), but there was significant variability across categories and dimensions. Finally, the taxonomy predicted the LLMs' internal evaluations of social categories (e.g., how positively/negatively the categories were represented), supporting the relevance of a multidimensional taxonomy for characterizing LLM stereotypes. Our findings suggest that high-dimensional human stereotypes are reflected in LLMs and must be considered in AI auditing and debiasing to minimize unidentified harms from reliance in low-dimensional views of bias in LLMs.

Hand-wearable robots, specifically exoskeletons, are designed to aid hands in daily activities, playing a crucial role in post-stroke rehabilitation and assisting the elderly. Our contribution to this field is a textile robotic glove with integrated actuators. These actuators, powered by pneumatic pressure, guide the user's hand to a desired position. Crafted from textile materials, our soft robotic glove prioritizes safety, lightweight construction, and user comfort. Utilizing the ruffles technique, integrated actuators guarantee high performance in blocking force and bending effectiveness. Here, we present a participant study confirming the effectiveness of our robotic device on a healthy participant group, exploiting EMG sensing.

Learning from distributed data without accessing them is undoubtedly a challenging and non-trivial task. Nevertheless, the necessity for distributed training of a statistical model has been increasing, due to the privacy concerns of local data owners and the cost in centralizing the massively distributed data. Federated learning (FL) is currently the de facto standard of training a machine learning model across heterogeneous data owners, without leaving the raw data out of local silos. Nevertheless, several challenges must be addressed in order for FL to be more practical in reality. Among these challenges, the statistical heterogeneity problem is the most significant and requires immediate attention. From the main objective of FL, three major factors can be considered as starting points -- \textit{parameter}, textit{mixing coefficient}, and \textit{local data distributions}. In alignment with the components, this dissertation is organized into three parts. In Chapter II, a novel personalization method, \texttt{SuPerFed}, inspired by the mode-connectivity is introduced. In Chapter III, an adaptive decision-making algorithm, \texttt{AAggFF}, is introduced for inducing uniform performance distributions in participating clients, which is realized by online convex optimization framework. Finally, in Chapter IV, a collaborative synthetic data generation method, \texttt{FedEvg}, is introduced, leveraging the flexibility and compositionality of an energy-based modeling approach. Taken together, all of these approaches provide practical solutions to mitigate the statistical heterogeneity problem in data-decentralized settings, paving the way for distributed systems and applications using collaborative machine learning methods.

Medical imaging segmentation is a highly active area of research, with deep learning-based methods achieving state-of-the-art results in several benchmarks. However, the lack of standardized tools for training, testing, and evaluating new methods makes the comparison of methods difficult. To address this, we introduce the Medical Imaging Segmentation Toolkit (MIST), a simple, modular, and end-to-end medical imaging segmentation framework designed to facilitate consistent training, testing, and evaluation of deep learning-based medical imaging segmentation methods. MIST standardizes data analysis, preprocessing, and evaluation pipelines, accommodating multiple architectures and loss functions. This standardization ensures reproducible and fair comparisons across different methods. We detail MIST's data format requirements, pipelines, and auxiliary features and demonstrate its efficacy using the BraTS Adult Glioma Post-Treatment Challenge dataset. Our results highlight MIST's ability to produce accurate segmentation masks and its scalability across multiple GPUs, showcasing its potential as a powerful tool for future medical imaging research and development.

There are two recent trends in transportation and the broader science/engineering fields, which make the headlines almost every day. The first one is the emergence of connected/automated vehicles (CAVs) that i) may introduce new, complex traffic dynamics and interactions in the current and future traffic streams, and ii) generate increasingly available and massive datasets from both vehicles and the infrastructure. The second trend is the rapid development and application of deep learning techniques that seem to revolutionize almost every aspect of technology, science, engineering, and the entire society. While there have been numerous studies and applications of deep learning in transportation, in the paper, we are interested in the question of whether deep learning can help discover traffic dynamics (car-following models in particular) from data directly with no or little human involvement. An affirmative answer to this question will not only help discover/develop traffic dynamics models in this era but also have important implications for other science/engineering fields where dynamical systems and their governing equations are widely used and studied. Car-following depicts the driving behavior of how a vehicle (driver) follows and interacts with the vehicle in front of it. It is one of the basic traffic models in revealing traffic dynamics characteristics at the microscopic traffic flow level Brackstone and McDonald [1999]. Car-following studies can be traced back to the 1950s and 1960s when Pipes [1953], Chandler et al. [1958], Kometani and Sasaki [1958], Gazis et al. [1959, 1961], and Helly [1959] initiated an era of modeling car-following and traffic dynamics.

Incorporating a temporal dimension into pretrained image diffusion models for video generation is a prevalent approach. However, this method is computationally demanding and necessitates large-scale video datasets. More critically, the heterogeneity between image and video datasets often results in catastrophic forgetting of the image expertise. Recent attempts to directly extract video snippets from image diffusion models have somewhat mitigated these problems. Nevertheless, these methods can only generate brief video clips with simple movements and fail to capture fine-grained motion or non-grid deformation. In this paper, we propose a novel Zero-Shot video Sampling algorithm, denoted as $\mathcal{ZS}^2$, capable of directly sampling high-quality video clips from existing image synthesis methods, such as Stable Diffusion, without any training or optimization. Specifically, $\mathcal{ZS}^2$ utilizes the dependency noise model and temporal momentum attention to ensure content consistency and animation coherence, respectively. This ability enables it to excel in related tasks, such as conditional and context-specialized video generation and instruction-guided video editing. Experimental results demonstrate that $\mathcal{ZS}^2$ achieves state-of-the-art performance in zero-shot video generation, occasionally outperforming recent supervised methods. Homepage: \url{https://densechen.github.io/zss/}.

Conversational Speech Synthesis (CSS) aims to express a target utterance with the proper speaking style in a user-agent conversation setting. Existing CSS methods employ effective multi-modal context modeling techniques to achieve empathy understanding and expression. However, they often need to design complex network architectures and meticulously optimize the modules within them. In addition, due to the limitations of small-scale datasets containing scripted recording styles, they often fail to simulate real natural conversational styles. To address the above issues, we propose a novel generative expressive CSS system, termed GPT-Talker.We transform the multimodal information of the multi-turn dialogue history into discrete token sequences and seamlessly integrate them to form a comprehensive user-agent dialogue context. Leveraging the power of GPT, we predict the token sequence, that includes both semantic and style knowledge, of response for the agent. After that, the expressive conversational speech is synthesized by the conversation-enriched VITS to deliver feedback to the user.Furthermore, we propose a large-scale Natural CSS Dataset called NCSSD, that includes both naturally recorded conversational speech in improvised styles and dialogues extracted from TV shows. It encompasses both Chinese and English languages, with a total duration of 236 hours.We conducted comprehensive experiments on the reliability of the NCSSD and the effectiveness of our GPT-Talker. Both subjective and objective evaluations demonstrate that our model outperforms other state-of-the-art CSS systems significantly in terms of naturalness and expressiveness. The Code, Dataset, and Pre-trained Model are available at: https://github.com/AI-S2-Lab/GPT-Talker.

Ophthalmology consultations are crucial for diagnosing, treating, and preventing eye diseases. However, the growing demand for consultations exceeds the availability of ophthalmologists. By leveraging large pre-trained language models, we can design effective dialogues for specific scenarios, aiding in consultations. Traditional fine-tuning strategies for question-answering tasks are impractical due to increasing model size and often ignoring patient-doctor role function during consultations. In this paper, we propose EyeDoctor, an ophthalmic medical questioning large language model that enhances accuracy through doctor-patient role perception guided and an augmented knowledge base with external disease information. Experimental results show EyeDoctor achieves higher question-answering precision in ophthalmology consultations. Notably, EyeDoctor demonstrated a 7.25% improvement in Rouge-1 scores and a 10.16% improvement in F1 scores on multi-round datasets compared to second best model ChatGPT, highlighting the importance of doctor-patient role differentiation and dynamic knowledge base expansion for intelligent medical consultations. EyeDoc also serves as a free available web based service and souce code is available at https://github.com/sperfu/EyeDoc.