Uncertainty-aware Reward Design Process

Designing effective reward functions is a cornerstone of reinforcement learning (RL), yet it remains a challenging process due to the inefficiencies and inconsistencies inherent in conventional reward engineering methodologies. Recent advances have explored leveraging large language models (LLMs) to automate reward function design. However, their suboptimal performance in numerical optimization often yields unsatisfactory reward quality, while the evolutionary search paradigm demonstrates inefficient utilization of simulation resources, resulting in prohibitively lengthy design cycles with disproportionate computational overhead. To address these challenges, we propose the Uncertainty-aware Reward Design Process (URDP), a novel framework that integrates large language models to streamline reward function design and evaluation in RL environments. URDP quantifies candidate reward function uncertainty based on self-consistency analysis, enabling simulation-free identification of ineffective reward components while discovering novel reward components. Furthermore, we introduce uncertainty-aware Bayesian optimization (UABO), which incorporates uncertainty estimation to significantly enhance hyperparameter configuration efficiency. Finally, we construct a bi-level optimization architecture by decoupling the reward component optimization and the hyperparameter tuning. URDP orchestrates synergistic collaboration between the reward logic reasoning of the LLMs and the numerical optimization strengths of the Bayesian Optimization. We conduct a comprehensive evaluation of URDP across 35 diverse tasks spanning three benchmark environments. Our experimental results demonstrate that URDP not only generates higher-quality reward functions but also achieves significant improvements in the efficiency of automated reward design compared to existing approaches.

Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence

The collection and release of street-level recordings as Open Data play a vital role in advancing autonomous driving systems and AI research. However, these datasets pose significant privacy risks, particularly for pedestrians, due to the presence of Personally Identifiable Information (PII) that extends beyond biometric traits such as faces. In this paper, we present cRID, a novel cross-modal framework combining Large Vision-Language Models, Graph Attention Networks, and representation learning to detect textual describable clues of PII and enhance person re-identification (Re-ID). Our approach focuses on identifying and leveraging interpretable features, enabling the detection of semantically meaningful PII beyond low-level appearance cues. We conduct a systematic evaluation of PII presence in person image datasets. Our experiments show improved performance in practical cross-dataset Re-ID scenarios, notably from Market-1501 to CUHK03-np (detected), highlighting the framework's practical utility. Code is available at https://github.com/RAufschlaeger/cRID.

ConLID: Supervised Contrastive Learning for Low-Resource Language Identification

Language identification (LID) is a critical step in curating multilingual LLM pretraining corpora from web crawls. While many studies on LID model training focus on collecting diverse training data to improve performance, low-resource languages -- often limited to single-domain data, such as the Bible -- continue to perform poorly. To resolve these class imbalance and bias issues, we propose a novel supervised contrastive learning (SCL) approach to learn domain-invariant representations for low-resource languages. Through an extensive analysis, we show that our approach improves LID performance on out-of-domain data for low-resource languages by 3.2%, demonstrating its effectiveness in enhancing LID models.

Large Language Model-Driven Code Compliance Checking in Building Information Modeling

This research addresses the time-consuming and error-prone nature of manual code compliance checking in Building Information Modeling (BIM) by introducing a Large Language Model (LLM)-driven approach to semi-automate this critical process. The developed system integrates LLMs such as GPT, Claude, Gemini, and Llama, with Revit software to interpret building codes, generate Python scripts, and perform semi-automated compliance checks within the BIM environment. Case studies on a single-family residential project and an office building project demonstrated the system's ability to reduce the time and effort required for compliance checks while improving accuracy. It streamlined the identification of violations, such as non-compliant room dimensions, material usage, and object placements, by automatically assessing relationships and generating actionable reports. Compared to manual methods, the system eliminated repetitive tasks, simplified complex regulations, and ensured reliable adherence to standards. By offering a comprehensive, adaptable, and cost-effective solution, this proposed approach offers a promising advancement in BIM-based compliance checking, with potential applications across diverse regulatory documents in construction projects.

Arabic Dialect Classification using RNNs, Transformers, and Large Language Models: A Comparative Analysis

The Arabic language is among the most popular languages in the world with a huge variety of dialects spoken in 22 countries. In this study, we address the problem of classifying 18 Arabic dialects of the QADI dataset of Arabic tweets. RNN models, Transformer models, and large language models (LLMs) via prompt engineering are created and tested. Among these, MARBERTv2 performed best with 65% accuracy and 64% F1-score. Through the use of state-of-the-art preprocessing techniques and the latest NLP models, this paper identifies the most significant linguistic issues in Arabic dialect identification. The results corroborate applications like personalized chatbots that respond in users' dialects, social media monitoring, and greater accessibility for Arabic communities.

OpenWildlife: Open-Vocabulary Multi-Species Wildlife Detector for Geographically-Diverse Aerial Imagery

We introduce OpenWildlife (OW), an open-vocabulary wildlife detector designed for multi-species identification in diverse aerial imagery. While existing automated methods perform well in specific settings, they often struggle to generalize across different species and environments due to limited taxonomic coverage and rigid model architectures. In contrast, OW leverages language-aware embeddings and a novel adaptation of the Grounding-DINO framework, enabling it to identify species specified through natural language inputs across both terrestrial and marine environments. Trained on 15 datasets, OW outperforms most existing methods, achieving up to \textbf{0.981} mAP50 with fine-tuning and \textbf{0.597} mAP50 on seven datasets featuring novel species. Additionally, we introduce an efficient search algorithm that combines k-nearest neighbors and breadth-first search to prioritize areas where social species are likely to be found. This approach captures over \textbf{95\%} of species while exploring only \textbf{33\%} of the available images. To support reproducibility, we publicly release our source code and dataset splits, establishing OW as a flexible, cost-effective solution for global biodiversity assessments.

HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction

Real-time human perception is crucial for effective human-robot interaction (HRI). Large vision-language models (VLMs) offer promising generalizable perceptual capabilities but often suffer from high latency, which negatively impacts user experience and limits VLM applicability in real-world scenarios. To systematically study VLM capabilities in human perception for HRI and performance-latency trade-offs, we introduce HRIBench, a visual question-answering (VQA) benchmark designed to evaluate VLMs across a diverse set of human perceptual tasks critical for HRI. HRIBench covers five key domains: (1) non-verbal cue understanding, (2) verbal instruction understanding, (3) human-robot object relationship understanding, (4) social navigation, and (5) person identification. To construct HRIBench, we collected data from real-world HRI environments to curate questions for non-verbal cue understanding, and leveraged publicly available datasets for the remaining four domains. We curated 200 VQA questions for each domain, resulting in a total of 1000 questions for HRIBench. We then conducted a comprehensive evaluation of both state-of-the-art closed-source and open-source VLMs (N=11) on HRIBench. Our results show that, despite their generalizability, current VLMs still struggle with core perceptual capabilities essential for HRI. Moreover, none of the models within our experiments demonstrated a satisfactory performance-latency trade-off suitable for real-time deployment, underscoring the need for future research on developing smaller, low-latency VLMs with improved human perception capabilities. HRIBench and our results can be found in this Github repository: https://github.com/interaction-lab/HRIBench.

Fake or Real, Can Robots Tell? Evaluating Embodied Vision-Language Models on Real and 3D-Printed Objects

Robotic scene understanding increasingly relies on vision-language models (VLMs) to generate natural language descriptions of the environment. In this work, we present a comparative study of captioning strategies for tabletop scenes captured by a robotic arm equipped with an RGB camera. The robot collects images of objects from multiple viewpoints, and we evaluate several models that generate scene descriptions. We compare the performance of various captioning models, like BLIP and VLMs. Our experiments examine the trade-offs between single-view and multi-view captioning, and difference between recognising real-world and 3D printed objects. We quantitatively evaluate object identification accuracy, completeness, and naturalness of the generated captions. Results show that VLMs can be used in robotic settings where common objects need to be recognised, but fail to generalise to novel representations. Our findings provide practical insights into deploying foundation models for embodied agents in real-world settings.

Measuring and Guiding Monosemanticity

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in reliably localizing and manipulating feature representations. Sparse Autoencoders (SAEs) have recently emerged as a promising direction for feature extraction at scale, yet they, too, are limited by incomplete feature isolation and unreliable monosemanticity. To systematically quantify these limitations, we introduce Feature Monosemanticity Score (FMS), a novel metric to quantify feature monosemanticity in latent representation. Building on these insights, we propose Guided Sparse Autoencoders (G-SAE), a method that conditions latent representations on labeled concepts during training. We demonstrate that reliable localization and disentanglement of target concepts within the latent space improve interpretability, detection of behavior, and control. Specifically, our evaluations on toxicity detection, writing style identification, and privacy attribute recognition show that G-SAE not only enhances monosemanticity but also enables more effective and fine-grained steering with less quality degradation. Our findings provide actionable guidelines for measuring and advancing mechanistic interpretability and control of LLMs.

Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs

Test-time scaling has recently emerged as a promising approach for enhancing the reasoning capabilities of large language models or vision-language models during inference. Although a variety of test-time scaling strategies have been proposed, and interest in their application to the medical domain is growing, many critical aspects remain underexplored, including their effectiveness for vision-language models and the identification of optimal strategies for different settings. In this paper, we conduct a comprehensive investigation of test-time scaling in the medical domain. We evaluate its impact on both large language models and vision-language models, considering factors such as model size, inherent model characteristics, and task complexity. Finally, we assess the robustness of these strategies under user-driven factors, such as misleading information embedded in prompts. Our findings offer practical guidelines for the effective use of test-time scaling in medical applications and provide insights into how these strategies can be further refined to meet the reliability and interpretability demands of the medical domain.