arXiv:2604.04741v1 Announce Type: cross
Abstract: Public higher education systems face increasing financial pressures from expanding student populations, rising operational costs, and persistent demands for equitable access. Artificial Intelligence (A…
arXiv:2604.03260v1 Announce Type: new
Abstract: We introduce Focus, a method that learns which token pairs matter rather than approximating all of them. Learnable centroids assign tokens to groups; distant attention is restricted to same-group pairs w…
arXiv:2604.04839v1 Announce Type: new
Abstract: Neural machine translation (NMT) from Chinese to low-resource Southeast Asian languages remains severely constrained by the extreme scarcity of clean parallel corpora and the pervasive noise in existing …
arXiv:2512.12087v2 Announce Type: replace
Abstract: The growing demand for long-context inference capabilities in Large Language Models (LLMs) has intensified the computational and memory bottlenecks inherent to the self-attention mechanism. To addres…
arXiv:2604.02563v1 Announce Type: new
Abstract: Robots that traverse natural terrain must interpret contact forces generated under highly dynamic conditions. However, most terrain characterization approaches rely on quasi-static assumptions that negle…
arXiv:2604.03096v1 Announce Type: new
Abstract: Off-road autonomous navigation demands reliable 3D perception for robust obstacle detection in challenging unstructured terrain. While LiDAR is accurate, it is costly and power-intensive. Monocular depth…
arXiv:2509.19579v2 Announce Type: replace
Abstract: Outdoor intelligent autonomous robotic operation relies on a sufficiently expressive map of the environment. Classical geometric mapping methods retain essential structural environment information, b…
arXiv:2604.02878v1 Announce Type: new
Abstract: In GNSS-denied underwater environments, individual unmanned underwater vehicles (UUVs) suffer from unbounded dead-reckoning drift, making collaborative navigation crucial for accurate state estimation. H…
arXiv:2604.02911v1 Announce Type: new
Abstract: Achieving quadruped robot locomotion across diverse and dynamic terrains presents significant challenges, primarily due to the discrepancies between simulation environments and real-world conditions. Tra…
arXiv:2604.03006v1 Announce Type: new
Abstract: Learning the inverse dynamics of soft continuum robots remains challenging due to high-dimensional nonlinearities and complex actuation coupling. Conventional feedback-based controllers often suffer from…