arXiv:2603.05921v1 Announce Type: cross Abstract: This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level similarity, under the assumption that backdoor-triggered generations exhibit strong consistency across samples. However, they struggle to generalize to recently emerging backdoor attacks, […]
Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs
arXiv:2506.13082v4 Announce Type: replace Abstract: Moral competence is the ability to act in accordance with moral principles. As large language models (LLMs) are increasingly deployed in situations demanding moral competence, there is increasing interest in evaluating this ability empirically. We review existing literature and identify three significant shortcoming: (i) Over-reliance on prepackaged moral scenarios with […]
Addressing the Ecological Fallacy in Larger LMs with Human Context
arXiv:2603.05928v1 Announce Type: cross Abstract: Language model training and inference ignore a fundamental linguistic fact — there is a dependence between multiple sequences of text written by the same person. Prior work has shown that addressing this form of textitecological fallacy can greatly improve the performance of multiple smaller (~124M) GPT-based models. In this work, […]
XAI for Coding Agent Failures: Transforming Raw Execution Traces into Actionable Insights
arXiv:2603.05941v1 Announce Type: cross Abstract: Large Language Model (LLM)-based coding agents show promise in automating software development tasks, yet they frequently fail in ways that are difficult for developers to understand and debug. While general-purpose LLMs like GPT can provide ad-hoc explanations of failures, raw execution traces remain challenging to interpret even for experienced developers. […]
Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models
arXiv:2603.05953v1 Announce Type: cross Abstract: Mental health is not a fixed trait but a dynamic process shaped by the interplay between individual dispositions and situational contexts. Building on interactionist and constructionist psychological theories, we develop interpretable models to predict well-being and identify adaptive and maladaptive self-states in longitudinal social media data. Our approach integrates person-level […]
Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models
arXiv:2603.05963v1 Announce Type: cross Abstract: Recent advances in large-scale pretrained vision models have demonstrated impressive capabilities across a wide range of downstream tasks, including cross-modal and multi-modal scenarios. However, their direct application to 3D human skeleton data remains challenging due to fundamental differences in data format. Moreover, the scarcity of large-scale skeleton datasets and the […]
Multimodal Mixture-of-Experts with Retrieval Augmentation for Protein Active Site Identification
arXiv:2603.01511v2 Announce Type: replace Abstract: Accurate identification of protein active sites at the residue level is crucial for understanding protein function and advancing drug discovery. However, current methods face two critical challenges: vulnerability in single-instance prediction due to sparse training data, and inadequate modality reliability estimation that leads to performance degradation when unreliable modalities dominate […]
Technical Report: Automated Optical Inspection of Surgical Instruments
arXiv:2603.05987v1 Announce Type: cross Abstract: In the dynamic landscape of modern healthcare, maintaining the highest standards in surgical instruments is critical for clinical success. This report explores the diverse realm of surgical instruments and their associated manufacturing defects, emphasizing their pivotal role in ensuring the safety of surgical procedures. With potentially fatal consequences arising from […]
MM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMs
arXiv:2603.05997v1 Announce Type: cross Abstract: Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across variables. Existing ISTS forecasting methods often solely utilize historical observations to predict future ones while falling short in learning contextual semantics and fine-grained temporal patterns. To address these problems, we achieve MM-ISTS, […]
Predictive Coding Networks and Inference Learning: Tutorial and Survey
arXiv:2407.04117v3 Announce Type: replace-cross Abstract: Recent years have witnessed a growing call for renewed emphasis on neuroscience-inspired approaches in artificial intelligence research, under the banner of NeuroAI. A prime example of this is predictive coding networks (PCNs), based on the neuroscientific framework of predictive coding. This framework views the brain as a hierarchical Bayesian inference […]
Demystifying KAN for Vision Tasks: The RepKAN Approach
arXiv:2603.06002v1 Announce Type: cross Abstract: Remote sensing image classification is essential for Earth observation, yet standard CNNs and Transformers often function as uninterpretable black-boxes. We propose RepKAN, a novel architecture that integrates the structural efficiency of CNNs with the non-linear representational power of KANs. By utilizing a dual-path design — Spatial Linear and Spectral Non-linear […]
Sensitivity-Aware Retrieval-Augmented Intent Clarification
arXiv:2603.06025v1 Announce Type: cross Abstract: In conversational search systems, a key component is to determine and clarify the intent behind complex queries. We view intent clarification in light of the exploratory search paradigm, where users, through an iterative, evolving process of selection, exploration and retrieval, transform a visceral or conscious need into a formalized one. […]