Stay updated with the latest research and technology news
arXiv:2603.01586v1 Announce Type: new Abstract: Emerging unified editing models have demonstrated strong capabilities in general object editing tasks. However, it remains a significant challenge to...
arXiv:2603.01587v1 Announce Type: new Abstract: The growing integration of electric vehicle (EV) fleets into transportation services and energy systems requires accurate modeling of battery discharge...
arXiv:2603.01588v1 Announce Type: new Abstract: Due to their efficiency and small size, decision trees and random forests are popular machine learning models used for classification...
arXiv:2603.01589v1 Announce Type: new Abstract: The success of large language models (LLMs) in scientific domains has heightened safety concerns, prompting numerous benchmarks to evaluate their...
arXiv:2603.01590v1 Announce Type: new Abstract: Click-through rate (CTR) models in advertising and recommendation systems rely heavily on item ID embeddings, which struggle in item cold-start...
arXiv:2603.01591v1 Announce Type: new Abstract: Training-free diffusion priors enable inverse-problem solvers without retraining, but for nonlinear forward operators data consistency often relies on repeated derivatives...
arXiv:2603.01592v1 Announce Type: new Abstract: We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target...
arXiv:2603.01593v1 Announce Type: new Abstract: Dashcam videos collected by autonomous or assisted-driving systems are increasingly shared for safety auditing and model improvement. Even when explicit...
arXiv:2603.01594v1 Announce Type: new Abstract: Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific...
arXiv:2603.01596v1 Announce Type: new Abstract: Modern software relies heavily on third-party software libraries to streamline the development process. The act of switching one library for...
arXiv:2603.01598v1 Announce Type: new Abstract: Graph-centric cross-model data integration and analytics (GCDIA) refer to tasks that leverage the graph model as a central paradigm to...
arXiv:2603.01599v1 Announce Type: new Abstract: Quantization-Aware Pre-Training (QAPT) is an effective technique to reduce the compute and memory overhead of Deep Neural Networks while improving...
arXiv:2603.01600v1 Announce Type: new Abstract: In this paper, we study an optimal boundary control problem for the Boussinesq equations, which couple the time-dependent Navier-Stokes system...
arXiv:2603.01601v1 Announce Type: new Abstract: Large 3D reconstruction models have revolutionized the 3D content generation field, enabling broad applications in virtual reality and gaming. Just...
arXiv:2603.01602v1 Announce Type: new Abstract: Human vision exhibits remarkable adaptability in perceiving objects under camouflage. When color cues become unreliable, the visual system instinctively shifts...
arXiv:2603.01603v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables efficient training and fast novel view synthesis in static environments. To address challenges posed by...
arXiv:2603.01605v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong performance in visual recognition, yet their decision-making remains difficult to interpret. We propose BiCAM, a...
arXiv:2603.01607v1 Announce Type: new Abstract: Large visual language models (VLMs) have shown strong multi-modal medical reasoning ability, but most operate as end-to-end black boxes, diverging...
arXiv:2603.01608v1 Announce Type: new Abstract: As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming:...
arXiv:2603.01611v1 Announce Type: new Abstract: In this paper, we investigate the coordination of vehicle maneuvers in mixed-traffic corridors where connected and automated vehicles, human-driven vehicles,...
arXiv:2603.01613v1 Announce Type: new Abstract: Monocular re-localization plays a crucial role in enabling intelligent agents to achieve human-like perception. However, traditional methods rely on dense...
arXiv:2603.01615v1 Announce Type: new Abstract: The b-posit, or bounded posit, is a variation of the posit format designed for high performance computing (HPC) and AI...
arXiv:2603.01616v1 Announce Type: new Abstract: Discussions surrounding Artificial General Intelligence have largely focused on technical feasibility, timelines, and existential risk, often treating its social impact...
arXiv:2603.01620v1 Announce Type: new Abstract: Tool-integrated reasoning agents interleaving natural language deliberation with external API calls show promise for complex multi-step tasks. However, aligning such...