Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries, many real-world information needs require synthesizing multiple pieces of evidence. We introduce "integrative grounding" -- the challenge of retrieving and verifying multiple inter-dependent pieces of evidence to support a hypothesis query. To systematically study this problem, we repurpose data from four domains for evaluating integrative grounding capabilities. Our investigation reveals two critical findings: First, in groundedness verification, while LLMs are robust to redundant evidence, they tend to rationalize using internal knowledge when information is incomplete. Second, in examining retrieval planning strategies, we find that undirected planning can degrade performance through noise introduction, while premise abduction emerges as a promising approach due to its logical constraints. Additionally, LLMs' zero-shot self-reflection capabilities consistently improve grounding quality. These insights provide valuable direction for developing more effective integrative grounding systems.

Large Language Models (LLMs) often exhibit sycophancy, distorting responses to align with user beliefs, notably by readily agreeing with user counterarguments. Paradoxically, LLMs are increasingly adopted as successful evaluative agents for tasks such as grading and adjudicating claims. This research investigates that tension: why do LLMs show sycophancy when challenged in subsequent conversational turns, yet perform well when evaluating conflicting arguments presented simultaneously? We empirically tested these contrasting scenarios by varying key interaction patterns. We find that state-of-the-art models: (1) are more likely to endorse a user's counterargument when framed as a follow-up from a user, rather than when both responses are presented simultaneously for evaluation; (2) show increased susceptibility to persuasion when the user's rebuttal includes detailed reasoning, even when the conclusion of the reasoning is incorrect; and (3) are more readily swayed by casually phrased feedback than by formal critiques, even when the casual input lacks justification. Our results highlight the risk of relying on LLMs for judgment tasks without accounting for conversational framing.

Large Language Models (LLMs) with hundreds of billions of parameters have exhibited human-like intelligence by learning from vast amounts of internet-scale data. However, the uninterpretability of large-scale neural networks raises concerns about the reliability of LLM. Studies have attempted to assess the psychometric properties of LLMs by borrowing concepts from human psychology to enhance their interpretability, but they fail to account for the fundamental differences between LLMs and humans. This results in high rejection rates when human scales are reused directly. Furthermore, these scales do not support the measurement of LLM psychological property variations in different languages. This paper introduces AIPsychoBench, a specialized benchmark tailored to assess the psychological properties of LLM. It uses a lightweight role-playing prompt to bypass LLM alignment, improving the average effective response rate from 70.12% to 90.40%. Meanwhile, the average biases are only 3.3% (positive) and 2.1% (negative), which are significantly lower than the biases of 9.8% and 6.9%, respectively, caused by traditional jailbreak prompts. Furthermore, among the total of 112 psychometric subcategories, the score deviations for seven languages compared to English ranged from 5% to 20.2% in 43 subcategories, providing the first comprehensive evidence of the linguistic impact on the psychometrics of LLM.

Foundation models pretrained on physiological data such as photoplethysmography (PPG) signals are increasingly used to improve heart rate (HR) prediction across diverse settings. Fine-tuning these models for local deployment is often seen as a practical and scalable strategy. However, its impact on demographic fairness--particularly under domain shifts--remains underexplored. We fine-tune PPG-GPT -- a transformer-based foundation model pretrained on intensive care unit (ICU) data -- across three heterogeneous datasets (ICU, wearable, smartphone) and systematically evaluate the effects on HR prediction accuracy and gender fairness. While fine-tuning substantially reduces mean absolute error (up to 80%), it can simultaneously widen fairness gaps, especially in larger models and under significant distributional characteristics shifts. To address this, we introduce FairTune, a bias-aware fine-tuning framework in which we benchmark three mitigation strategies: class weighting based on inverse group frequency (IF), Group Distributionally Robust Optimization (GroupDRO), and adversarial debiasing (ADV). We find that IF and GroupDRO significantly reduce fairness gaps without compromising accuracy, with effectiveness varying by deployment domain. Representation analyses further reveal that mitigation techniques reshape internal embeddings to reduce demographic clustering. Our findings highlight that fairness does not emerge as a natural byproduct of fine-tuning and that explicit mitigation is essential for equitable deployment of physiological foundation models.

Falls among seniors are a major public health issue. Existing solutions using wearable sensors, ambient sensors, and RGB-based vision systems face challenges in reliability, user compliance, and practicality. Studies indicate that stakeholders, such as older adults and eldercare facilities, prefer non-wearable, passive, privacy-preserving, and real-time fall detection systems that require no user interaction. This study proposes an advanced thermal fall detection method using a Bidirectional Convolutional Long Short-Term Memory (BiConvLSTM) model, enhanced with spatial, temporal, feature, self, and general attention mechanisms. Through systematic experimentation across hundreds of model variations exploring the integration of attention mechanisms, recurrent modules, and motion flow, we identified top-performing architectures. Among them, BiConvLSTM achieved state-of-the-art performance with a ROC-AUC of $99.7\%$ on the TSF dataset and demonstrated robust results on TF-66, a newly emerged, diverse, and privacy-preserving benchmark. These results highlight the generalizability and practicality of the proposed model, setting new standards for thermal fall detection and paving the way toward deployable, high-performance solutions.

Large language models (LLMs) have achieved promising results in tabular data generation. However, inherent historical biases in tabular datasets often cause LLMs to exacerbate fairness issues, particularly when multiple advantaged and protected features are involved. In this work, we introduce a universal debiasing framework that minimizes group-level dependencies by simultaneously reducing the mutual information between advantaged and protected attributes. By leveraging the autoregressive structure and analytic sampling distributions of LLM-based tabular data generators, our approach efficiently computes mutual information, reducing the need for cumbersome numerical estimations. Building on this foundation, we propose two complementary methods: a direct preference optimization (DPO)-based strategy, namely UDF-DPO, that integrates seamlessly with existing models, and a targeted debiasing technique, namely UDF-MIX, that achieves debiasing without tuning the parameters of LLMs. Extensive experiments demonstrate that our framework effectively balances fairness and utility, offering a scalable and practical solution for debiasing in high-stakes applications.

We explore the potential for combining generative AI with grammar-based visualizations for biomedical data discovery. In our prototype, we use a multi-agent system to generate visualization specifications and apply filters. These visualizations are linked together, resulting in an interactive dashboard that is progressively constructed. Our system leverages the strengths of natural language while maintaining the utility of traditional user interfaces. Furthermore, we utilize generated interactive widgets enabling user adjustment. Finally, we demonstrate the potential utility of this system for biomedical data discovery with a case study.

Video-to-text and text-to-video retrieval are dominated by English benchmarks (e.g. DiDeMo, MSR-VTT) and recent multilingual corpora (e.g. RUDDER), yet Arabic remains underserved, lacking localized evaluation metrics. We introduce a three-stage framework, AutoArabic, utilizing state-of-the-art large language models (LLMs) to translate non-Arabic benchmarks into Modern Standard Arabic, reducing the manual revision required by nearly fourfold. The framework incorporates an error detection module that automatically flags potential translation errors with 97% accuracy. Applying the framework to DiDeMo, a video retrieval benchmark produces DiDeMo-AR, an Arabic variant with 40,144 fluent Arabic descriptions. An analysis of the translation errors is provided and organized into an insightful taxonomy to guide future Arabic localization efforts. We train a CLIP-style baseline with identical hyperparameters on the Arabic and English variants of the benchmark, finding a moderate performance gap (about 3 percentage points at Recall@1), indicating that Arabic localization preserves benchmark difficulty. We evaluate three post-editing budgets (zero/ flagged-only/ full) and find that performance improves monotonically with more post-editing, while the raw LLM output (zero-budget) remains usable. To ensure reproducibility to other languages, we made the code available at https://github.com/Tahaalshatiri/AutoArabic.

In the manufacturing industry, it is very important to keep machines and processes running smoothly and without unexpected problems. One of the most common tools used to check if everything is working properly is called Statistical Process Control (SPC). Traditional SPC methods work by checking whether recent measurements are within acceptable limits. However, they only react after a problem has already occurred. This can lead to wasted materials, machine downtime, and increased costs. In this paper, we present a smarter way to use SPC. Instead of just reacting to issues after they happen, our system can predict future problems before they occur. We use a machine learning tool called Facebook Prophet, which is designed to work with time-series data (data that changes over time). Prophet looks at past data and forecasts what the next value will be. Then, we use SPC rules to decide if the predicted value is in a Safe zone (no problem), a Warning zone (needs attention), or a Critical zone (may require shutting down the process). We applied this system to real data from a semiconductor manufacturing company. One of the challenges with this data is that the measurements are not taken at regular time intervals. This makes it harder to predict future values accurately. Despite this, our model was able to make strong predictions and correctly classify the risk level of future measurements. The main benefit of our system is that it gives engineers and technicians a chance to act early - before something goes wrong. This helps reduce unexpected failures and improves the overall stability and reliability of the production process. By combining machine learning with traditional SPC, we make quality control more proactive, accurate, and useful for modern industry.

Coordinated multi-robot navigation is essential for robots to operate as a team in diverse environments. During navigation, robot teams usually need to maintain specific formations, such as circular formations to protect human teammates at the center. However, in complex scenarios such as narrow corridors, rigidly preserving predefined formations can become infeasible. Therefore, robot teams must be capable of dynamically splitting into smaller subteams and adaptively controlling the subteams to navigate through such scenarios while preserving formations. To enable this capability, we introduce a novel method for SubTeaming and Adaptive Formation (STAF), which is built upon a unified hierarchical learning framework: (1) high-level deep graph cut for team splitting, (2) intermediate-level graph learning for facilitating coordinated navigation among subteams, and (3) low-level policy learning for controlling individual mobile robots to reach their goal positions while avoiding collisions. To evaluate STAF, we conducted extensive experiments in both indoor and outdoor environments using robotics simulations and physical robot teams. Experimental results show that STAF enables the novel capability for subteaming and adaptive formation control, and achieves promising performance in coordinated multi-robot navigation through challenging scenarios. More details are available on the project website: https://hcrlab.gitlab.io/project/STAF.