arXiv:2603.04427v4 Announce Type: replace Abstract: Standard Transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations (value transfer). We show that…
arXiv:2603.26891v1 Announce Type: new Abstract: AI arenas, which rank generative models from pairwise preferences of users, are a popular method for measuring the relative performance of models in the course of their organic use. Because rankings are computed from noisy…
arXiv:2603.22300v2 Announce Type: replace Abstract: Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these approaches consistently…
arXiv:2603.26931v1 Announce Type: new Abstract: Machine learning models often struggle to generalize across domains with varying data distributions, such as differing noise levels, leading to degraded performance. Traditional strategies like personalized training, which trains separate models per domain, and joint…
arXiv:2501.00277v2 Announce Type: replace-cross Abstract: Modern AI algorithms require labeled data. In real world, majority of data are unlabeled. Labeling the data are costly. this is particularly true for some areas requiring special skills, such as reading radiology images by…
By quickly generating aesthetically accurate previews of fabricated objects, the VisiPrint system could make prototyping faster and less wasteful.
arXiv:2603.27743v1 Announce Type: cross Abstract: Empirical likelihood is an attractive inferential framework that respects natural parameter boundaries, but existing approaches typically require smoothness of the functional and miscalibrate substantially when these assumptions are violated. For the optimal-value functional central to…
arXiv:2510.19372v2 Announce Type: replace-cross Abstract: We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $ell$ actions before deciding its course of action. While such predictive information…
arXiv:2603.09645v2 Announce Type: replace-cross Abstract: Photonic Quantum Machine Learning (PQML) is an emerging method to implement scalable, energy-efficient quantum information processing by combining photonic quantum computing technologies with machine learning techniques. The features of photonic technologies offer several benefits: room-temperature…
By quickly generating aesthetically accurate previews of fabricated objects, the VisiPrint system could make prototyping faster and less wasteful.
