arXiv:2601.09859v1 Announce Type: new Abstract: CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: Can we improve the performance of open-weight CLIP models across various downstream tasks using only existing self-supervised datasets? Unlike supervised fine-tuning, which adapts a pretrained model to a single downstream task, our setting seeks to improve general performance across various tasks. […]

Ver mais

arXiv:2602.12406v1 Announce Type: new Abstract: Interacting with multiple objects simultaneously makes us fast. A pre-step to this interaction is to select the objects, i.e., multi-object selection, which is enabled through two steps: (1) toggling multi-selection mode — mode-switching — and then (2) selecting all the intended objects — subselection. In extended reality (XR), each step can be performed with the eyes, hands, and voice. To examine how design choices affect user performance, we evaluated four mode-switching (SemiPinch, FullPinch, […]

Ver mais

arXiv:2502.07396v2 Announce Type: replace-cross Abstract: The performance of the Monte Carlo sampling methods relies on the crucial choice of a proposal density. The notion of optimality is fundamental to design suitable adaptive procedures of the proposal density within Monte Carlo schemes. This work is an exhaustive review around the concept of optimality in importance sampling. Several frameworks are described and analyzed, such as the marginal likelihood approximation for model selection, the use of multiple proposal densities, a sequence […]

Ver mais

The average reward is a fundamental performance metric in reinforcement learning (RL) focusing on the long-run performance of an agent. Differential temporal difference (TD) learning algorithms are a major advance for average reward RL as they provide an efficient online method to learn the value functions associated with the average reward in both on-policy and off-policy settings. However, existing convergence guarantees require a local clock in learning rates tied to state visit counts, which practitioners do not use […]

Ver mais

arXiv:2601.06025v1 Announce Type: new Abstract: We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of sampled point clouds under a manifold assumption. Graph convolution is defined spectrally via the graph Laplacian, whose low-frequency spectrum approximates that of the Laplace-Beltrami operator of the underlying smooth manifold, and shallow GCNNs of possibly infinite width are linear functionals on the space of measures on the parameter space. From this functional-analytic perspective, graph […]

Ver mais

Accurate molecular property prediction requires integrating complementary information from molecular structure and chemical semantics. In this work, we propose LGM-CL, a local-global multimodal contrastive learning framework that jointly models molecular graphs and textual representations derived from SMILES and chemistry-aware augmented texts. Local functional group information and global molecular topology are captured using AttentiveFP and Graph Transformer encoders, respectively, and aligned through self-supervised contrastive learning. In addition, chemically enriched textual descriptions are contrasted with original SMILES to incorporate physicochemical […]

Ver mais

In most enterprise Databricks environments (like in MSC or large analytics ecosystems), system tables such as system.jobrunlogs or system.cluster_events may be restricted or disabled due to security or governance policies. However, tracking cluster utilization and cost is crucial for : Understanding how efficiently jobs use compute Identifying idle clusters or cost leaks Forecasting infrastructure budget Building custom cost dashboards This blog demonstrates a step-by-step approach to compute cluster utilization and cost using only Databricks REST APIs — no […]

Ver mais