arXiv:2505.23745v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer learning scenarios, VLMs remain…
arXiv:2509.19391v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is widely used to efficiently adapt Transformers by adding trainable low-rank matrices to attention projections. While effective, these matrices are considered independent for each attention projection (Query, Key, and Value) and each…
arXiv:2412.14480v2 Announce Type: replace-cross Abstract: In Embodied Question Answering (EQA), agents must explore and develop a semantic understanding of an unseen environment to answer a situated question with confidence. This problem remains challenging in robotics, due to the difficulties in…
arXiv:2509.19362v1 Announce Type: new Abstract: Feature attribution is essential for interpreting deep learning models, particularly in time-series domains such as healthcare, biometrics, and human-AI interaction. However, standard attribution methods, such as Integrated Gradients or SHAP, are computationally intensive and not…
arXiv:2509.19363v1 Announce Type: new Abstract: Credit card fraud is assuming growing proportions as a major threat to the financial position of American household, leading to unpredictable changes in household economic behavior. To solve this problem, in this paper, a new…
arXiv:2509.19366v1 Announce Type: new Abstract: This study investigates the effectiveness of unsupervised outlier detection methods in audit analytics, utilizing USA spending data from the U.S. Department of Health and Human Services (DHHS) as a case example. We employ and compare…
arXiv:2509.19375v1 Announce Type: new Abstract: Despite their widespread applications, Large Language Models (LLMs) often struggle to express uncertainty, posing a challenge for reliable deployment in high stakes and safety critical domains like clinical diagnostics. Existing standard baseline methods such as…
arXiv:2509.19372v1 Announce Type: new Abstract: We critically assess the efficacy of the current SOTA in hallucination detection and find that its performance on the RAGTruth dataset is largely driven by a spurious correlation with data. Controlling for this effect, state-of-the-art…
arXiv:2509.19379v1 Announce Type: new Abstract: Imitation Learning (IL) algorithms offer an efficient way to train an agent by mimicking an expert’s behavior without requiring a reward function. IL algorithms often necessitate access to state and action information from expert demonstrations.…
arXiv:2509.19376v1 Announce Type: new Abstract: We address temporal failures in RAG systems using two methods on cybersecurity data. A simple recency prior achieved an accuracy of 1.00 on freshness tasks. In contrast, a clustering heuristic for topic evolution failed (0.08…
