Stay updated with the latest research and technology news
arXiv:2512.15774v2 Announce Type: replace Abstract: Data scarcity and distribution shift pose major challenges for masked face detection and recognition. We propose a two-step generative data...
arXiv:2512.15829v2 Announce Type: replace Abstract: Working memory enables the brain to integrate transient information for rapid decision-making. Artificial networks typically replicate this via recurrent or...
arXiv:2512.17979v2 Announce Type: replace Abstract: Industrial symbiosis fosters circularity by enabling firms to repurpose residual resources, yet its emergence is constrained by socio-spatial frictions that...
arXiv:2512.18956v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks through long Chain-of-Thought (CoT) reasoning. Extending these successes...
arXiv:2512.19027v2 Announce Type: replace Abstract: Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces...
arXiv:2512.19131v2 Announce Type: replace Abstract: Decentralized federated learning (DFL) enables collaborative model training across edge devices without centralized coordination, offering resilience against single points of...
arXiv:2512.20352v2 Announce Type: replace Abstract: Qualitative research faces a critical reliability challenge: traditional inter-rater agreement methods require multiple human coders, are time-intensive, and often yield...
arXiv:2512.20677v3 Announce Type: replace Abstract: The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating robustness against adversarial...
arXiv:2512.20871v2 Announce Type: replace Abstract: Implicit neural representations for videos (NeRV) have shown strong potential for video compression. However, applying NeRV to high-resolution 360-degree videos...
arXiv:2512.20885v2 Announce Type: replace Abstract: Accurate prediction of flow delay is essential for optimizing and managing modern communication networks. We investigate three levels of modeling...
arXiv:2512.20980v2 Announce Type: replace Abstract: Long-tailed pulmonary anomalies in chest radiography present formidable diagnostic challenges. Despite the recent strides in diffusion-based methods for enhancing the...
arXiv:2512.21787v2 Announce Type: replace Abstract: Dialectal Arabic to Modern Standard Arabic (DA-MSA) translation is a challenging task in Machine Translation (MT) due to significant lexical,...
arXiv:2512.22136v2 Announce Type: replace Abstract: Distributed deep neural networks (DNNs) have become central to modern computer vision, yet their deployment on resource-constrained edge devices remains...
arXiv:2512.22420v2 Announce Type: replace Abstract: Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it...
arXiv:2601.00097v3 Announce Type: replace Abstract: We design a large-language-model (LLM) agent system that extracts causal feedback fuzzy cognitive maps (FCMs) from raw text. The causal...
arXiv:2601.00204v2 Announce Type: replace Abstract: 3D morphing remains challenging due to the difficulty of generating semantically consistent and temporally smooth deformations, especially across categories. We...
arXiv:2601.01068v2 Announce Type: replace Abstract: As quantum computing advances, the cryptographic algorithms that underpin confidentiality, integrity, and authentication in Intelligent Transportation Systems (ITS) face increasing...
arXiv:2601.01112v2 Announce Type: replace Abstract: We introduce EmoLoom-2B, a lightweight and reproducible pipeline that turns small language models under 2B parameters into fast screening candidates...
arXiv:2601.01710v2 Announce Type: replace Abstract: We propose an algorithm for counting below-threshold triangles in weighted graphs under local weight differential privacy. While prior work has...
arXiv:2601.02085v2 Announce Type: replace Abstract: Strawberry harvesting robots faced persistent challenges such as low integration of visual perception, fruit-gripper misalignment, empty grasping/misgrasp, and strawberry slippage...
arXiv:2601.02158v2 Announce Type: replace Abstract: This paper presents FormationEval, an open multiple-choice question benchmark for evaluating language models on petroleum geoscience and subsurface disciplines. The...
arXiv:2601.02744v3 Announce Type: replace Abstract: While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term...
arXiv:2601.03213v3 Announce Type: replace Abstract: Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically...
arXiv:2601.04911v2 Announce Type: replace Abstract: The primary objective of a diverse planning approach is to generate a set of plans that are distinct from one...