Stay updated with the latest research and technology news
arXiv:2602.09499v1 Announce Type: new Abstract: We study the computational relationship between replicability (Impagliazzo et al. [STOC `22], Ghazi et al. [NeurIPS `21]) and other stability...
arXiv:2602.09501v1 Announce Type: new Abstract: Masked Diffusion Language Models (MDLMs) generate text by iteratively filling masked tokens, requiring two coupled decisions at each step: which...
arXiv:2602.09502v1 Announce Type: new Abstract: To expand the applicability of decentralized online learning, previous studies have proposed several algorithms for decentralized online continuous submodular maximization...
arXiv:2602.09505v1 Announce Type: new Abstract: Regularizing a linear ill-posed operator equation can be achieved by manipulating the spectrum of the operator's pseudo-inverse. Tikhonov regularization and...
arXiv:2602.09506v1 Announce Type: new Abstract: Contrastive learning (CL) is a predominant technique in image classification, but they showed limited performance with an imbalanced dataset. Recently,...
arXiv:2602.09507v1 Announce Type: new Abstract: Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical...
arXiv:2602.09509v1 Announce Type: new Abstract: Knowledge Distillation (KD) has emerged as a powerful technique for model compression, enabling lightweight student networks to benefit from the...
arXiv:2602.09510v1 Announce Type: new Abstract: We propose AdaDS, a generalizable framework for depth super-resolution that robustly recovers high-resolution depth maps from arbitrarily degraded low-resolution inputs....
arXiv:2602.09514v1 Announce Type: new Abstract: Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being...
arXiv:2602.09515v1 Announce Type: new Abstract: This paper presents an Internet of Things (IoT) application that utilizes an AI classifier for fast-object detection using the frame...
arXiv:2602.09516v1 Announce Type: new Abstract: The CheckThat! lab aims to advance the development of innovative technologies combating disinformation and manipulation efforts in online communication across...
arXiv:2602.09517v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks by employing search-augmented reasoning to incorporate external knowledge...
arXiv:2602.09518v1 Announce Type: new Abstract: Analyzing animal and human behavior has long been a challenging task in computer vision. Early approaches from the 1970s to...
arXiv:2602.09520v1 Announce Type: new Abstract: The Rashomon set captures the collection of models that achieve near-identical empirical performance yet may differ substantially in their decision...
arXiv:2602.09521v1 Announce Type: new Abstract: Existing Large Vision-Language Models (LVLMs) exhibit insufficient visual attention, leading to hallucinations. To alleviate this problem, some previous studies adjust...
arXiv:2602.09522v1 Announce Type: new Abstract: Rapid eating is common yet difficult to regulate in situ, partly because people seldom notice pace changes and sustained self-monitoring...
arXiv:2602.09523v1 Announce Type: new Abstract: We present Singpath-VL, a vision-language large model, to fill the vacancy of AI assistant in cervical cytology. Recent advances in...
arXiv:2602.09524v1 Announce Type: new Abstract: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detection is...
arXiv:2602.09528v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have achieved significant success across various domains. However, their use in high-stakes...
arXiv:2602.09529v1 Announce Type: new Abstract: Automated change detection in remote sensing imagery is critical for urban management, environmental monitoring, and disaster assessment. While deep learning...
arXiv:2602.09530v1 Announce Type: new Abstract: We introduce AutoSpec, a neural network framework for discovering iterative spectral algorithms for large-scale numerical linear algebra and numerical optimization....
arXiv:2602.09531v1 Announce Type: new Abstract: Blind Image Quality Assessment, aiming to replicate human perception of visual quality without reference, plays a key role in vision...
arXiv:2602.09532v1 Announce Type: new Abstract: Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex...
arXiv:2602.09533v1 Announce Type: new Abstract: Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However,...