Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 07569v1 Announce Type: new Abstract: Accurate carbon emission monitoring is critical for climate policy and emerging regulatory mechanisms such as the EU Carbon Border Adjustment Mechanism, yet city-level high-frequency monitoring data remain extremely scarce, severely limiting data-hungry deep learning models.
arXiv:2606. 07953v1 Announce Type: new Abstract: Large-scale Visual-Language Models (LVLMs) have achieved remarkable success in natural visual tasks, yet their application to industrial defect detection remains challenging due to two fundamental limitations: (i) the scarcity of large-scale industrial datasets that cover diverse defect categories across multiple domains, and (ii) the reliance on manual prompts (points, boxes, masks) that introduce subjective noise and lack text-visual interaction for fine-grained understanding.
arXiv:2606. 06554v2 Announce Type: replace-cross Abstract: Reliable polymer identification is essential for ensuring the quality and safety of recycled plastics, yet conventional sorting and spectroscopic techniques often struggle to deliver robust discrimination.
arXiv:2605. 21028v2 Announce Type: replace-cross Abstract: Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors.
arXiv:2606. 08063v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions.
arXiv:2606. 09409v1 Announce Type: new Abstract: Pairwise comparisons combined with aggregation methods like Elo have become central to evaluating generative models, yet concerns remain that they reward superficial stylistic cues or display judge biases.
arXiv:2606. 09012v1 Announce Type: cross Abstract: Post-training quantization (PTQ) converts a trained full-precision model into low-bit weights without task-level retraining, while quantization-aware training (QAT) incorporates quantization into the training loop.
arXiv:2606. 07640v1 Announce Type: cross Abstract: This study investigates the trade-offs between fidelity, privacy, and utility in synthetic data generation under conditions of data scarcity and privacy sensitivity.
arXiv:2606. 07929v1 Announce Type: new Abstract: Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes.
arXiv:2606. 07874v1 Announce Type: new Abstract: LLMs-as-judges are the only way to evaluate safety at scale.
arXiv:2601. 04266v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics.
arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.
arXiv:2606. 08855v1 Announce Type: new Abstract: This paper examines the limitations of fully digital and partially digital e-assessment approaches in summative examinations in higher education.
arXiv:2606. 08292v1 Announce Type: new Abstract: In mechanistic interpretability, attention heads are commonly elevated to role claims (e.
arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.
arXiv:2606. 08669v1 Announce Type: cross Abstract: Voice biometric systems face growing threats from spoofing attacks, yet the evaluation of detection models remains inconsistent across datasets.
arXiv:2407. 01718v2 Announce Type: replace-cross Abstract: Embedding high-dimensional data into a low-dimensional space is an indispensable component of data analysis.
arXiv:2606. 08388v1 Announce Type: new Abstract: Muon replaces a matrix gradient $G=U\Sigma V^\top$ by its polar factor $UV^\top$.
arXiv:2509. 12760v5 Announce Type: replace Abstract: We introduce the Similarity-Distance-Magnitude (SDM) activation function, a more robust and interpretable formulation of the standard softmax activation function, adding Similarity (i.
arXiv:2606. 08596v1 Announce Type: new Abstract: Constructing efficient and reliable policies to assist humans is indispensable for human-AI collaboration.