Stay updated with the latest research and technology news
arXiv:2603.04461v1 Announce Type: new Abstract: Precipitation nowcasting (short-term forecasting) is still often performed using numerical solvers for physical equations, which are computationally expensive and make...
arXiv:2603.04463v1 Announce Type: new Abstract: Sampling-based motion planning algorithms are widely used for motion planning of robotic manipulators, but they often struggle with sample inefficiency...
arXiv:2603.04464v1 Announce Type: new Abstract: In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain...
arXiv:2603.04466v1 Announce Type: new Abstract: Can a multimodal language model learn to manipulate physical objects by reasoning about its own failures-without gradient updates, demonstrations, or...
arXiv:2603.04469v1 Announce Type: new Abstract: Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and...
arXiv:2603.04470v1 Announce Type: new Abstract: Embodied navigation in underground mines faces significant challenges, including narrow passages, uneven terrain, near-total darkness, GPS-denied conditions, and limited communication...
arXiv:2603.04472v1 Announce Type: new Abstract: Accurate predictions of ship trajectories in crowded environments are essential to ensure safety in inland waterways traffic. Recent advances in...
arXiv:2603.04474v1 Announce Type: new Abstract: Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor...
arXiv:2603.04476v1 Announce Type: new Abstract: Modern EDA flows rely heavily on Tcl scripting, yet general LLMs perform poorly in this domain due to extreme data...
arXiv:2603.04477v1 Announce Type: new Abstract: Smart insoles equipped with pressure sensors, accelerometers, and gyroscopes offer a non-intrusive means of monitoring human gait and posture. We...
arXiv:2603.04478v1 Announce Type: new Abstract: Pretraining for electroencephalogram (EEG) foundation models has predominantly relied on self-supervised masked reconstruction, a paradigm largely adapted from and inspired...
arXiv:2603.04484v1 Announce Type: new Abstract: Efficient code retrieval is critical for developer productivity, yet existing benchmarks largely focus on Python and rarely stress-test robustness beyond...
arXiv:2603.04509v1 Announce Type: new Abstract: Recognition of daily activities is a critical element for effective Ambient Assisted Living (AAL) systems, particularly to monitor the well-being...
arXiv:2603.04512v1 Announce Type: new Abstract: We investigate preservation results for the independent fusion of one-variable first-order modal logics. We show that, without equality, Kripke completeness...
arXiv:2603.04514v1 Announce Type: new Abstract: Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize...
arXiv:2603.04516v1 Announce Type: new Abstract: Astronomers have acquired vast repositories of multimodal data, including images, spectra, and time series, complemented by decades of literature that...
arXiv:2603.04528v1 Announce Type: new Abstract: Mathematical concepts emerge through an interplay of processes, including experimentation, efforts at proof, and counterexamples. In this paper, we present...
arXiv:2603.04530v1 Announce Type: new Abstract: Relative entropy is a fundamental class of distances between probability distributions, with widespread applications in probability theory, statistics, and machine...
arXiv:2603.04531v1 Announce Type: new Abstract: Tactile dexterous manipulation is essential to automating complex household tasks, yet learning effective control policies remains a challenge. While recent...
arXiv:2603.04532v1 Announce Type: new Abstract: Information retrieval (IR) benchmarks typically follow the Cranfield paradigm, relying on static and predefined corpora. However, temporal changes in technical...
arXiv:2603.04534v1 Announce Type: new Abstract: Social norms are stable behavioral patterns that emerge endogenously within economic systems through repeated interactions among agents. In online market...
arXiv:2603.04537v1 Announce Type: new Abstract: Generative AI has been heavily critiqued by artists in both popular media and HCI scholarship. However, more work is needed...
arXiv:2603.04538v1 Announce Type: new Abstract: State-of-the-art EfficientSCI loses 20.58 dB when its assumed forward operator deviates from physical reality in just eight parameters, yet no...
arXiv:2603.04545v1 Announce Type: new Abstract: Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference...