Stay updated with the latest research and technology news
arXiv:2507.09095v3 Announce Type: replace Abstract: Multimodal fusion (MMF) plays a critical role in the perception of autonomous driving, which primarily fuses camera and LiDAR streams...
arXiv:2507.11245v5 Announce Type: replace Abstract: With the rapid development of foundation video generation technologies, long video generation models have exhibited promising research potential thanks to...
arXiv:2507.12307v2 Announce Type: replace Abstract: The Golub-Kahan-Tikhonov method is a popular solution technique for large linear discrete ill-posed problems. This method first applies partial Golub-Kahan...
arXiv:2507.14266v2 Announce Type: replace Abstract: Over the past decade, higher education has undergone successive shifts driven by three major developments: Massive Open Online Courses (MOOCs),...
arXiv:2507.15335v2 Announce Type: replace Abstract: Industrial defect detection systems face critical limitations when confined to one-class anomaly detection paradigms, which assume uniform outlier distributions and...
arXiv:2507.18923v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) effectively synthesizes novel views through its flexible representation, yet fails to accurately reconstruct scene geometry. While...
arXiv:2507.19146v2 Announce Type: replace Abstract: Autonomous driving faces challenges in navigating complex real-world traffic, requiring safe handling of both common and critical scenarios. Reinforcement learning...
arXiv:2507.19229v2 Announce Type: replace Abstract: The modeling of genomic sequences presents unique challenges due to their length and structural complexity. Traditional sequence models struggle to...
arXiv:2507.19883v2 Announce Type: replace Abstract: Autonomous driving promises safer roads, reduced congestion, and improved mobility, yet validating these systems across diverse conditions remains a major...
arXiv:2507.20230v3 Announce Type: replace Abstract: To fully expedite AI-powered chemical research, high-quality chemical databases are the foundation. Automatic extraction of chemical information from the literature...
arXiv:2507.23428v5 Announce Type: replace Abstract: We propose the *State Space Neural Operator* (SS-NO), a compact architecture for learning solution operators of time-dependent partial differential equations...
arXiv:2508.01653v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have achieved impressive performance in multimodal tasks, but they still suffer from hallucinations, i.e., generating content...
arXiv:2508.02833v4 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO), recently introduced by DeepSeek, is a critic-free reinforcement learning algorithm for fine-tuning large language models....
arXiv:2508.03351v2 Announce Type: replace Abstract: Post-training quantization (PTQ) has emerged as an effective technique for compressing large models and accelerating inference without retraining. While PTQ...
arXiv:2508.03381v2 Announce Type: replace Abstract: This paper investigates unequal error protection (UEP) in digital semantic communication, where semantically important bits require substantially higher reliability than...
arXiv:2508.05264v5 Announce Type: replace Abstract: Infrared and visible image fusion (IVIF) aims to combine the thermal radiation information from infrared images with the rich texture...
arXiv:2508.08759v2 Announce Type: replace Abstract: Kernel methods are versatile tools for function approximation and surrogate modeling. In particular, greedy techniques offer computational efficiency and reliability...
arXiv:2508.09425v3 Announce Type: replace Abstract: An important limitation of Inverter-Based Resources (IBR) is their reduced contribution to Short-Circuit Current (SCC), as compared to that of...
arXiv:2508.10154v2 Announce Type: replace Abstract: Mixture models have attracted significant attention due to practical effectiveness and comprehensive theoretical foundations. A persisting challenge is model misspecification,...
arXiv:2508.13238v3 Announce Type: replace Abstract: Recent advances in vision-language models (VLMs) have enabled end-to-end document parsing and understanding, achieving strong performance on diverse optical character...
arXiv:2508.14457v2 Announce Type: replace Abstract: Blockchain networks offer decentralization, transparency, and immutability for managing critical data but encounter scalability problems as the number of network...
arXiv:2508.14625v4 Announce Type: replace Abstract: Scientific workflows are critical to scientific data analysis and often involve computationally intensive processing of large datasets on compute clusters....
arXiv:2508.18093v2 Announce Type: replace Abstract: We present a case study evaluating large language models (LLMs) with 128K-token context windows on a technical question answering (QA)...
arXiv:2508.21287v3 Announce Type: replace Abstract: Subgraph isomorphism is a fundamental problem in graph analysis that seeks to find all instances of a pattern graph within...