Latent Labels
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models
arXiv:2605.30393v1 Announce Type: new Abstract: Public numeric benchmarks appear in pretraining, so an evaluation that conditions on a date may be measuring memorized recall rather than out-of-sample skill. We introduce NumLeak, a measurement framework that combines API-boundary probes on production models with a white-box controlled validation on an open causal LM. Top-tier frontier LLMs recall the Fama-French market excess return at 3-seed pooled Pearson r=0.97-0.99 while staying within...
Pool-Select-Refine: Allocation-Aware Generative Dataset Distillation with Soft-Label-Guided Latent Refinement
Announce Type: new Abstract: Diffusion-based dataset distillation has recently emerged as a promising paradigm for condensing large-scale datasets into compact synthetic sets. By leveraging pretrained generative priors, these methods can produce realistic class-conditional samples more efficiently than traditional matching-based approaches. However, most existing diffusion-based methods still adopt a rigid ``Generate-and-Use'' strategy, where the generated samples are directly treated as the...
Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning
arXiv:2009.10277v2 Announce Type: replace Abstract: We propose a system for measuring hate speech on a continuous, interval-valued spectrum ranging from genocidal to supportive speech by combining supervised deep learning with faceted Rasch item response theory (IRT). We decompose the theoretical construct of hate speech into constituent concepts operationalized as 10 ordinal labels. Those labels are reconstituted via IRT probabilistic latent modeling into an interval outcome measure while...
PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction
Announce Type: replace Abstract: Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation trajectories and cannot exploit this unlabeled structure. We introduce \textbf{PI-JEPA} (Physics-Informed Joint Embedding Predictive Architecture), a surrogate...
PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction
Announce Type: replace-cross Abstract: Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation trajectories and cannot exploit this unlabeled structure. We introduce \textbf{PI-JEPA} (Physics-Informed Joint Embedding Predictive Architecture), a surrogate...
Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion Augmentation
Announce Type: new Abstract: Analyzing microstructural defects in transmission electron microscopy (TEM) images, particularly in irradiated metal alloys, is often limited by the availability of high-quality, labeled data. To address this, we introduce a generative data augmentation approach using a mask-conditioned latent diffusion model (LDM) for synthesizing realistic TEM images with controllable, automatically labeled multi-class defect masks. Without requiring manual annotations for...
STELLAR: Spatio-Temporal Environmental Learning with Latent Alignment and Refinement for Long-Tailed Species Distribution Modeling
Announce Type: new Abstract: Joint Species Distribution Modeling (JSDM) is a key enabler for biodiversity monitoring and conservation planning. However, accurate JSDM faces two coupled challenges: environmental drivers and species distributions are inherently spatio-temporal, while species co-occurrence patterns exhibit complex non-linear community structure and severe long-tail imbalance driven by rare species. Existing approaches often address these factors in isolation, learning from...
Implicit Regularization for Multi-label Feature Selection
arXiv:2411.11436v2 Announce Type: replace Abstract: In this paper, we address the problem of feature selection in the context of multi-label learning, by using a new estimator based on implicit regularization and label embedding. Unlike the sparse feature selection methods that use a penalized estimator with explicit regularization terms such as $l_{2,1}$-norm, MCP or SCAD, we propose a simple alternative method via Hadamard product parameterization. In order to guide the feature selection...
OpenRFM: Dissecting Relational In-Context Learning
arXiv:2606.04320v1 Announce Type: new Abstract: Relational Foundation Models (RFMs) promise a single pre-trained predictor that, given any relational database, returns predictions in one forward pass via relational in-context learning (ICL). Yet a substantial gap separates open RFMs from their commercial counterparts, and the origin of this gap has not been systematically understood. We dissect a representative framework, the Relational Transformer (RT), from two perspectives.
Drifting Models for Surrogate Flow Modeling
arXiv:2606.07481v1 Announce Type: new Abstract: While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration. To solve this problem generative surrogates offer better distribution modeling than deterministic networks, but iterative sampling is slow. To enable high-quality, single-pass generation, we adapt the novel generative drifting framework to fluid mechanics.