arXiv:2604.05830v1 Announce Type: cross Abstract: Voice-based interfaces are widely used; however, achieving fair Wake-up Word detection across diverse speaker populations remains a critical challenge due to persistent demographic biases. This study evaluates the effectiveness of demographics-agnostic training techniques in mitigating performance disparities among speakers of varying sex, age, and accent. We utilize the OK Aura […]
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer
arXiv:2604.06129v1 Announce Type: cross Abstract: This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates input tokens into a compact representation through a learned polynomial function, from which each token retrieves contextual information. We prove that PoM satisfies the contextual […]
ReLU Networks for Exact Generation of Similar Graphs
arXiv:2604.05929v1 Announce Type: cross Abstract: Generation of graphs constrained by a specified graph edit distance from a source graph is important in applications such as cheminformatics, network anomaly synthesis, and structured data augmentation. Despite the growing demand for such constrained generative models in areas including molecule design and network perturbation analysis, the neural architectures required […]
FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation–Full Version
arXiv:2604.05551v1 Announce Type: cross Abstract: Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment: few-step sampling for fast inference. In this study, we show that when models only have […]
CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments
arXiv:2604.06019v1 Announce Type: cross Abstract: The advancement of Large Language Models (LLMs) has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology (IT) environments, failing to capture the constraints, and specialized protocols of Operational Technology (OT). To address this gap, we introduce CritBench, a novel framework designed to […]
SemLink: A Semantic-Aware Automated Test Oracle for Hyperlink Verification using Siamese Sentence-BERT
arXiv:2604.05711v1 Announce Type: cross Abstract: Web applications rely heavily on hyperlinks to connect disparate information resources. However, the dynamic nature of the web leads to link rot, where targets become unavailable, and more insidiously, semantic drift, where a valid HTTP 200 connection exists, but the target content no longer aligns with the source context. Traditional […]
Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
arXiv:2604.06124v1 Announce Type: cross Abstract: This study proposes a lightweight multimodal adaptation framework to bridge the representation gap between RGB-pretrained VLMs and thermal infrared imagery, and demonstrates its practical utility using a real drone-collected dataset. A thermal dataset was developed from drone-collected imagery and was used to fine-tune VLMs through multimodal projector alignment, enabling the […]
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
arXiv:2508.16703v3 Announce Type: replace-cross Abstract: On-device running Large Language Models (LLMs) is nowadays a critical enabler towards preserving user privacy. We observe that the attention operator falls back from the special-purpose NPU to the general-purpose CPU/GPU because of quantization sensitivity in state-of-the-art frameworks. This fallback results in a degraded user experience and increased complexity in […]
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
arXiv:2604.06161v1 Announce Type: cross Abstract: Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantization. This loss of highlight and shadow detail precludes mapping accurate luminance to HDR displays and limits meaningful re-exposure in post-production […]
Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration
arXiv:2602.00913v3 Announce Type: replace-cross Abstract: Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether Schwartz higher-order (HO) categories help this setting on ValueEval’24 / ValuesML (74K English sentences) under a compute-frugal budget. Rather than proposing a new architecture, we compare direct supervised transformers, hard HO$rightarrow$values pipelines, Presence$rightarrow$HO$rightarrow$values cascades, compact […]
Generalizable Audio-Visual Navigation via Binaural Difference Attention and Action Transition Prediction
arXiv:2604.05007v1 Announce Type: cross Abstract: In Audio-Visual Navigation (AVN), agents must locate sound sources in unseen 3D environments using visual and auditory cues. However, existing methods often struggle with generalization in unseen scenarios, as they tend to overfit to semantic sound features and specific training environments. To address these challenges, we propose the textbfBinaural Difference […]
This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA
arXiv:2604.05051v1 Announce Type: cross Abstract: Patients are increasingly turning to large language models (LLMs) with medical questions that are complex and difficult to articulate clearly. However, LLMs are sensitive to prompt phrasings and can be influenced by the way questions are worded. Ideally, LLMs should respond consistently regardless of phrasing, particularly when grounded in the […]