arXiv:2603.11140v1 Announce Type: new Abstract: Fairness in machine learning research has largely focused on outcome-oriented fairness criteria such as Equalized Odds, while comparatively less attention has been given to procedural-oriented fairness, which addresses how a model arrives at its predictions.…
arXiv:2505.19240v4 Announce Type: replace-cross Abstract: Large language model (LLM) research has grown rapidly, along with increasing concern about their limitations. In this survey, we conduct a data-driven, semi-automated review of research on limitations of LLMs (LLLMs) from 2022 to early…
arXiv:2603.11142v1 Announce Type: new Abstract: The paper explores how video models trained for classification tasks represent nuanced, hidden semantic information that may not affect the final outcome, a key challenge for Trustworthy AI models. Through Explainable and Interpretable AI methods,…
arXiv:2511.04583v4 Announce Type: replace-cross Abstract: Understanding the current capabilities and risks of AI Scientist systems (autoresearch) is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the academic ecosystem. To this end, we develop Jr.…
arXiv:2603.11149v1 Announce Type: new Abstract: Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework…
arXiv:2603.01213v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as cooperating agents, yet their behavior in adversarial consensus settings has not been systematically studied. We evaluate LLM-based agents on a Byzantine consensus game over scalar values using a…
arXiv:2603.11161v1 Announce Type: new Abstract: We formally define Algorithmic Capture (i.e., “grokking” an algorithm) as the ability of a neural network to generalize to arbitrary problem sizes ($T$) with controllable error and minimal sample adaptation, distinguishing true algorithmic learning from…
arXiv:2603.11378v1 Announce Type: cross Abstract: We investigate continued pretraining (CPT) for adapting wav2vec2-bert-2.0 to Swahili automatic speech recognition (ASR). Our approach combines unlabeled audio with limited labeled data through pseudo-labeled CPT followed by supervised finetuning. With 20,000 labeled samples, we…
arXiv:2603.11168v1 Announce Type: new Abstract: Automatic speech recognition (ASR) for pathological speech remains underexplored, especially for Huntington’s disease (HD), where irregular timing, unstable phonation, and articulatory distortion challenge current models. We present a systematic HD-ASR study using a high-fidelity clinical…
arXiv:2603.11545v1 Announce Type: cross Abstract: We present an agentic AI framework for autonomous multimodal query processing that coordinates specialized tools across text, image, audio, video, and document modalities. A central Supervisor dynamically decomposes user queries, delegates subtasks to modality-appropriate tools…
