arXiv:2510.26994v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) promise more effective information extraction for review-based recommender systems, yet current methods still (i) mine free-form reviews without scope control, producing redundant and noisy representations, (ii) lack principled…
arXiv:2510.26709v2 Announce Type: replace Abstract: Communication remains a central bottleneck in large-scale distributed machine learning, and gradient sparsification has emerged as a promising strategy to alleviate this challenge. However, existing gradient compressors face notable limitations: Rand-$K$ discards structural information and…
arXiv:2510.26997v1 Announce Type: new Abstract: Learning rules — prescriptions for updating model parameters to improve performance — are typically assumed rather than derived. Why do some learning rules work better than others, and under what assumptions can a given rule…
arXiv:2502.10650v3 Announce Type: replace-cross Abstract: Advances in deep learning and representation learning have transformed item factor analysis (IFA) in the item response theory (IRT) literature by enabling more efficient and accurate parameter estimation. Variational Autoencoders (VAEs) have been one of…
arXiv:2510.27001v1 Announce Type: new Abstract: Multi-armed bandit (MAB) problems serve as a fundamental building block for more complex reinforcement learning algorithms. However, evaluating and comparing MAB algorithms remains challenging due to the lack of standardized conditions and replicability. This is…
arXiv:2505.24038v2 Announce Type: replace-cross Abstract: Recent advances in object detectors have led to their adoption for industrial uses. However, their deployment in safety-critical applications is hindered by the inherent lack of reliability of neural networks and the complex structure of…
arXiv:2510.27002v1 Announce Type: new Abstract: While world models are increasingly positioned as a pathway to overcoming data scarcity in domains such as robotics, open training infrastructure for world modeling remains nascent. We introduce Jasmine, a performant JAX-based world modeling codebase…
arXiv:2510.25327v3 Announce Type: replace-cross Abstract: Real-time multimodal inference on resource-constrained edge devices is essential for applications such as autonomous driving, human-computer interaction, and mobile health. However, prior work often overlooks the tight coupling between sensing dynamics and model execution, as…
arXiv:2510.27004v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models improve transformer efficiency but lack a unified theoretical explanation, especially when both feed-forward and attention layers are allowed to specialize. To this end, we study the Mixture-of-Transformers (MoT), a tractable theoretical framework…
arXiv:2303.03272v2 Announce Type: replace Abstract: Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of…
