Stay updated with the latest research and technology news
arXiv:2603.01960v1 Announce Type: new Abstract: TiledAttention is a scaled dot-product attention (SDPA) forward operator for SDPA research on NVIDIA GPUs. Implemented in cuTile Python (TileIR)...
arXiv:2603.01965v1 Announce Type: new Abstract: Multimodal Variational Autoencoders have emerged as a popular tool to extract effective representations from rich multimodal data. However, such models...
arXiv:2603.01966v1 Announce Type: new Abstract: Long-horizon interactions between users and LLM-based assistants necessitate effective memory management, yet current approaches face challenges in training and evaluation...
arXiv:2603.01968v1 Announce Type: new Abstract: Grokking, the sudden transition from memorization to generalization, is characterized by the emergence of low-dimensional representations, yet the mechanism underlying...
arXiv:2603.01972v1 Announce Type: new Abstract: Modern societal challenges, such as climate change, urbanization, and water resource management, demand integrated, multi-discipline, multi-problem approaches to frame and...
arXiv:2603.01974v1 Announce Type: new Abstract: TactileWalk evaluates dynamic electrotactile patterns on fingertips for wearable navigation. We developed a fingertip stimulation prototype featuring a 10x6 electrode...
arXiv:2603.01976v1 Announce Type: new Abstract: White blood cell (WBC) classification is fundamental for hematology applications such as infection assessment, leukemia screening, and treatment monitoring. However,...
arXiv:2603.01982v1 Announce Type: new Abstract: Magnetic Levitation (MagLev) systems fundamentally increase the flexibility of in-machine material flow in industrial automation. Therefore, these systems enable dynamic...
arXiv:2603.01984v1 Announce Type: new Abstract: In automatic music generation, a central challenge is to design controls that enable meaningful human-machine interaction. Existing systems often rely...
arXiv:2603.01986v1 Announce Type: new Abstract: We study the problem of computing a U-statistic with a kernel function f of degree k $\ge$ 2, i.e., the...
arXiv:2603.01990v1 Announce Type: new Abstract: Personalized AI assistants must recall and reason over long-term user memory, which naturally spans multiple modalities and sources such as...
arXiv:2603.01992v1 Announce Type: new Abstract: People's attitudes towards personal data sharing have been extensively researched, however, limited research studied their evolving nature in across different...
arXiv:2603.01993v1 Announce Type: new Abstract: Recent advances in generative AI have significantly enhanced the realism of multimodal media manipulation, thereby posing substantial challenges to manipulation...
arXiv:2603.01997v1 Announce Type: new Abstract: Event cameras provide high-temporal-resolution visual sensing that is well suited for observing fast-moving aerial objects; however, their use for drone...
arXiv:2603.01999v1 Announce Type: new Abstract: Reliable obstacle avoidance in industrial settings demands 3D scene understanding, but widely used 2D LiDAR sensors perceive only a single...
arXiv:2603.02001v1 Announce Type: new Abstract: Modern OLAP engines are designed to support arbitrary analytical workloads, but this generality incurs structural overhead, including runtime schema interpretation,...
arXiv:2603.02002v1 Announce Type: new Abstract: Foundation MLIPs demonstrate broad applicability across diverse material systems and have emerged as a powerful and transformative paradigm in chemical...
arXiv:2603.02004v1 Announce Type: new Abstract: Visuomotor navigation policies have shown strong perception-action coupling for embodied agents, yet they often struggle with safe navigation and dynamic...
arXiv:2603.02005v1 Announce Type: new Abstract: Graph diffusion models have gained significant attention in graph generation tasks, but they often inherit and amplify topology biases from...
arXiv:2603.02006v1 Announce Type: new Abstract: We introduce Kruskal-EDS (Edge Dynamic Stratification), a distribution-adaptive variant of Kruskal's minimum spanning tree (MST) algorithm that replaces the mandatory...
arXiv:2603.02008v1 Announce Type: new Abstract: Effective exploration in reinforcement learning requires not only tracking where an agent has been, but also understanding how the agent...
arXiv:2603.02010v1 Announce Type: new Abstract: Many differentially private (DP) data release systems either output DP synthetic data and leave analysts to perform inference as usual,...
arXiv:2603.02012v1 Announce Type: new Abstract: Low-dose Positron Emission Tomography (PET) reduces radiation exposure but suffers from severe noise and quantitative degradation. Diffusion-based denoising models achieve...
arXiv:2603.02015v1 Announce Type: new Abstract: Tabular synthetic data generators are typically trained to match observational distributions, which can yield high conventional utility (e.g., column correlations,...