Mental health issues among college students have reached critical levels, significantly impacting academic performance and overall wellbeing. Predicting and understanding mental health status among college students is challenging due to three main factors: the necessity for large-scale longitudinal datasets, the prevalence of black-box machine learning models lacking transparency, and the tendency of existing approaches to provide aggregated insights at the population level rather than individualized understanding. To tackle these challenges, this paper presents I-HOPE, the first Interpretable Hierarchical mOdel for Personalized mEntal health prediction. I-HOPE is a two-stage hierarchical model, validated on the College Experience Study, the longest longitudinal mobile sensing dataset. This dataset spans five years and captures data from both pre-pandemic periods and the COVID-19 pandemic. I-HOPE connects raw behavioral features to mental health status through five defined behavioral categories as interaction labels. This approach achieves a prediction accuracy of 91%, significantly surpassing the 60-70% accuracy of baseline methods. In addition, our model distills complex patterns into interpretable and individualized insights, enabling the future development of tailored interventions and improving mental health support. The code is available at https://github.com/roycmeghna/I-HOPE.

In this work, we study offline reinforcement learning (RL) with zero-shot generalization property (ZSG), where the agent has access to an offline dataset including experiences from different environments, and the goal of the agent is to train a policy over the training environments which performs well on test environments without further interaction. Existing work showed that classical offline RL fails to generalize to new, unseen environments. We propose pessimistic empirical risk minimization (PERM) and pessimistic proximal policy optimization (PPPO), which leverage pessimistic policy evaluation to guide policy learning and enhance generalization. We show that both PERM and PPPO are capable of finding a near-optimal policy with ZSG. Our result serves as a first step in understanding the foundation of the generalization phenomenon in offline reinforcement learning.

The widespread availability of large language models (LLMs), such as ChatGPT, has significantly impacted education, raising both opportunities and challenges. Students can frequently interact with LLM-powered, interactive learning tools, but their usage patterns need to be analyzed to ensure ethical usage of these tools. To better understand how students interact with LLMs in an academic setting, we introduce \textbf{StudyChat}, a publicly available dataset capturing real-world student interactions with an LLM-powered tutoring chatbot in a semester-long, university-level artificial intelligence (AI) course. We deploy a web application that replicates ChatGPT's core functionalities, and use it to log student interactions with the LLM while working on programming assignments. We collect 1,197 conversations, which we annotate using a dialogue act labeling schema inspired by observed interaction patterns and prior research. Additionally, we analyze these interactions, highlight behavioral trends, and analyze how specific usage patterns relate to course outcomes. \textbf{StudyChat} provides a rich resource for the learning sciences and AI in education communities, enabling further research into the evolving role of LLMs in education.

Geospatial question answering (QA) is a fundamental task in navigation and point of interest (POI) searches. While existing geospatial QA datasets exist, they are limited in both scale and diversity, often relying solely on textual descriptions of geo-entities without considering their geometries. A major challenge in scaling geospatial QA datasets for reasoning lies in the complexity of geospatial relationships, which require integrating spatial structures, topological dependencies, and multi-hop reasoning capabilities that most text-based QA datasets lack. To address these limitations, we introduce MapQA, a novel dataset that not only provides question-answer pairs but also includes the geometries of geo-entities referenced in the questions. MapQA is constructed using SQL query templates to extract question-answer pairs from OpenStreetMap (OSM) for two study regions: Southern California and Illinois. It consists of 3,154 QA pairs spanning nine question types that require geospatial reasoning, such as neighborhood inference and geo-entity type identification. Compared to existing datasets, MapQA expands both the number and diversity of geospatial question types. We explore two approaches to tackle this challenge: (1) a retrieval-based language model that ranks candidate geo-entities by embedding similarity, and (2) a large language model (LLM) that generates SQL queries from natural language questions and geo-entity attributes, which are then executed against an OSM database. Our findings indicate that retrieval-based methods effectively capture concepts like closeness and direction but struggle with questions that require explicit computations (e.g., distance calculations). LLMs (e.g., GPT and Gemini) excel at generating SQL queries for one-hop reasoning but face challenges with multi-hop reasoning, highlighting a key bottleneck in advancing geospatial QA systems.

Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.g., sparse training data availability) can permanently impair the learning performance of the global model owned by the model owner (i.e., the cloud server). However, strategies to motivate clients with high-quality contributions to join the FL training process and share trained model updates during CLPs remain underexplored. Additionally, existing incentive mechanisms in FL treat all training periods equally, which consequently fails to motivate clients to participate early. Compounding this challenge is the cloud's limited knowledge of client training capabilities due to privacy regulations, leading to information asymmetry. Therefore, in this article, we propose a time-aware incentive mechanism, called Right Reward Right Time (R3T), to encourage client involvement, especially during CLPs, to maximize the utility of the cloud in FL. Specifically, the cloud utility function captures the trade-off between the achieved model performance and payments allocated for clients' contributions, while accounting for clients' time and system capabilities, efforts, joining time, and rewards. Then, we analytically derive the optimal contract for the cloud and devise a CLP-aware mechanism to incentivize early participation and efforts while maximizing cloud utility, even under information asymmetry. By providing the right reward at the right time, our approach can attract the highest-quality contributions during CLPs. Simulation and proof-of-concept studies show that R3T increases cloud utility and is more economically effective than benchmarks. Notably, our proof-of-concept results show up to a 47.6% reduction in the total number of clients and up to a 300% improvement in convergence time while reaching competitive test accuracies compared with incentive mechanism benchmarks.

How do two individuals differ when performing the same action? In this work, we introduce Video Action Differencing (VidDiff), the novel task of identifying subtle differences between videos of the same action, which has many applications, such as coaching and skill learning. To enable development on this new task, we first create VidDiffBench, a benchmark dataset containing 549 video pairs, with human annotations of 4,469 fine-grained action differences and 2,075 localization timestamps indicating where these differences occur. Our experiments demonstrate that VidDiffBench poses a significant challenge for state-of-the-art large multimodal models (LMMs), such as GPT-4o and Qwen2-VL. By analyzing failure cases of LMMs on VidDiffBench, we highlight two key challenges for this task: localizing relevant sub-actions over two videos and fine-grained frame comparison. To overcome these, we propose the VidDiff method, an agentic workflow that breaks the task into three stages: action difference proposal, keyframe localization, and frame differencing, each stage utilizing specialized foundation models. To encourage future research in this new task, we release the benchmark at https://huggingface.co/datasets/jmhb/VidDiffBench and code at http://jmhb0.github.io/viddiff.

Speculative decoding is an effective method for accelerating inference of large language models (LLMs) by employing a small draft model to predict the output of a target model. However, when adapting speculative decoding to domain-specific target models, the acceptance rate of the generic draft model drops significantly due to domain shift. In this work, we systematically investigate knowledge distillation techniques for training domain draft models to improve their speculation accuracy. We compare white-box and black-box distillation approaches and explore their effectiveness in various data accessibility scenarios, including historical user queries, curated domain data, and synthetically generated alignment data. Our experiments across Function Calling, Biology, and Chinese domains show that offline distillation consistently outperforms online distillation by 11% to 25%, white-box distillation surpasses black-box distillation by 2% to 10%, and data scaling trends hold across domains. Additionally, we find that synthetic data can effectively align draft models and achieve 80% to 93% of the performance of training on historical user queries. These findings provide practical guidelines for training domain-specific draft models to improve speculative decoding efficiency.

One of the most vital cognitive skills to possess is the ability to make sense of objects, events, and situations in the world. In the current paper, we offer an approach for creating artificially intelligent agents with the capacity for sensemaking in novel environments. Objectives: to present several key ideas: (1) a novel unified conceptual framework for sensemaking (which includes the existence of sign relations embedded within and across frames); (2) interaction among various content-addressable, distributed-knowledge structures via shared attributes (whose net response would represent a synthesized object, event, or situation serving as a sign for sensemaking in a novel environment). Findings: we suggest that attributes across memories can be shared and recombined in novel ways to create synthesized signs, which can denote certain outcomes in novel environments (i.e., sensemaking).

This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously. To analyze explicit bias, we directly pose questions to VLMs related to gender and racial differences: (1) Multiple-choice questions based on a given image (e.g., "What is the education level of the person in the image?") (2) Yes-No comparisons using two images (e.g., "Is the person in the first image more educated than the person in the second image?") For implicit bias, we design tasks where VLMs assist users but reveal biases through their responses: (1) Image description tasks: Models are asked to describe individuals in images, and we analyze disparities in textual cues across demographic groups. (2) Form completion tasks: Models draft a personal information collection form with 20 attributes, and we examine correlations among selected attributes for potential biases. We evaluate Gemini-1.5, GPT-4V, GPT-4o, LLaMA-3.2-Vision and LLaVA-v1.6. Our code and data are publicly available at https://github.com/uscnlp-lime/VisBias.

Many studies exploring the adoption of Large Language Model-based tools for software development by junior developers have emerged in recent years. These studies have sought to understand developers' perspectives about using those tools, a fundamental pillar for successfully adopting LLM-based tools in Software Engineering. The aim of this paper is to provide an overview of junior software developers' perspectives and use of LLM-based tools for software engineering (LLM4SE). We conducted a systematic literature review (SLR) following guidelines by Kitchenham et al. on 56 primary studies, applying the definition for junior software developers as software developers with equal or less than five years of experience, including Computer Science/Software Engineering students. We found that the majority of the studies focused on comprehending the different aspects of integrating AI tools in SE. Only 8.9\% of the studies provide a clear definition for junior software developers, and there is no uniformity. Searching for relevant information is the most common task using LLM tools. ChatGPT was the most common LLM tool present in the studies (and experiments). A majority of the studies (83.9\%) report both positive and negative perceptions about the impact of adopting LLM tools. We also found and categorised advantages, challenges, and recommendations regarding LLM adoption. Our results indicate that developers are using LLMs not just for code generation, but also to improve their development skills. Critically, they are not just experiencing the benefits of adopting LLM tools, but they are also aware of at least a few LLM limitations, such as the generation of wrong suggestions, potential data leaking, and AI hallucination. Our findings offer implications for software engineering researchers, educators, and developers.