109

arXiv:2512.17446v1 Announce Type: new
Abstract: Injury prevention in sports requires understanding how bio-mechanical risks emerge from movement patterns captured in real-world scenarios. However, identifying and interpreting injury prone events from raw video remains difficult and time-consuming. …
111

arXiv:2512.17846v1 Announce Type: new
Abstract: We present Planning as Descent (PaD), a framework for offline goal-conditioned reinforcement learning that grounds trajectory synthesis in verification. Instead of learning a policy or explicit planner, PaD learns a goal-conditioned energy function ov…
211

arXiv:2512.17109v1 Announce Type: new
Abstract: Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature information during tr…
111

arXiv:2512.17229v1 Announce Type: new
Abstract: Long Video Question-Answering (LVQA) presents a significant challenge for Multi-modal Large Language Models (MLLMs) due to immense context and overloaded information, which could also lead to prohibitive memory consumption. While existing methods atte…
111

arXiv:2512.17708v1 Announce Type: cross
Abstract: Microelectromechanical systems (MEMS) speakers are compact, scalable alternatives to traditional voice coil speakers, promising improved sound quality through precise semiconductor manufacturing. This review provides an overview of the research land…
124

arXiv:2511.09801v2 Announce Type: replace-cross
Abstract: This work extends the recently introduced Alpha-Procrustes family of Riemannian metrics for symmetric positive definite (SPD) matrices by incorporating generalized versions of the Bures-Wasserstein (GBW), Log-Euclidean, and Wasserstein dista…
431

arXiv:2512.17136v1 Announce Type: new
Abstract: As the global population ages, many seniors face the problem of loneliness. Companion robots offer a potential solution. However, current companion robots often lack advanced functionality, while task-oriented robots are not designed for social intera…
109

arXiv:2505.17720v2 Announce Type: replace
Abstract: Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where machine learning models can now rival and even surpass traditional numerical simulations. Following the…
111

arXiv:2512.17850v1 Announce Type: new
Abstract: This chapter demonstrates how computational social science (CSS) tools are extending and expanding research on aging. The depth and context from traditionally qualitative methods such as participant observation, in-depth interviews, and historical doc…
220

arXiv:2412.20878v3 Announce Type: replace
Abstract: We present the first formal correctness proof of Edmonds' blossom shrinking algorithm for maximum cardinality matching in general graphs. We focus on formalising the mathematical structures and properties that allow the algorithm to run in worst-c…
109

arXiv:2501.11869v3 Announce Type: replace-cross
Abstract: Snapshot Compressive Imaging (SCI) uses coded masks to compress a 3D data cube into a single 2D snapshot. In practice, multiplexing can push intensities beyond the sensor's dynamic range, producing saturation that violates the linear SCI mod…
111

arXiv:2512.17128v1 Announce Type: new
Abstract: Interest in the hulls of linear codes has been growing rapidly. More is known when the inner product is Euclidean than Hermitian. A shift to the latter is gaining traction. The focus is on a code whose Hermitian hull dimension and dual distance can be…
111

arXiv:2512.17116v1 Announce Type: new
Abstract: Research in explorable uncertainty addresses combinatorial optimization problems where there is partial information about the values of numeric input parameters, and exact values of these parameters can be determined by performing costly queries. The …
222

arXiv:2507.18242v3 Announce Type: replace
Abstract: Despite their theoretical appeal, totally corrective boosting methods based on linear programming have received limited empirical attention. In this paper, we conduct the first large-scale experimental study of six LP-based boosting formulations, …