Home Knowledge Base Adaptive Data

Adaptive Data

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Data-Driven Adaptive Second-Order Sliding Mode Control with Noisy Data

Announce Type: replace Abstract: This paper proposes a data-driven approach to designing adaptive suboptimal second-order sliding mode (ASSOSM) controllers for a class of single-input nonlinear systems with partially unknown dynamics, subject to both matched and unmatched disturbances. We first view the system as comprising two coupled dynamics, referred to as the upper and lower dynamics, with the last state serving as a virtual input to the upper dynamics. The proposed control-design...

arXiv CS 2d ago

An Adaptive Data cleaning Framework for Noisy Label Detection

arXiv:2606.07086v1 Announce Type: new Abstract: Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets. In real-world applications, however, labels are often corrupted by ambiguity, human error, or dynamic environments. Over-parameterized DNNs easily memorize these noisy labels during training, degrading model accuracy and generalization.

arXiv CS 2d ago

Adapting Noise to Data: Generative Flows from 1D Processes

arXiv:2510.12636v5 Announce Type: replace-cross Abstract: The default Gaussian latent in flow-based generative models poses challenges when learning certain distributions such as heavy-tailed ones. We introduce a general framework for learning data-adaptive parametric prior distributions (latent noise) using one-dimensional quantile functions, optimized via the Wasserstein distance between noise and data. The quantile-based prior parameterization naturally adapts to both heavy-tailed and...

arXiv CS 7d ago

Diffusion Models for Adaptive Sequential Data Generation

arXiv:2606.06007v1 Announce Type: new Abstract: Generating realistic synthetic sequential data is critical in real-world applications across operations research, finance, healthcare, energy systems, and scientific computing, where time-indexed observations are used for prediction, simulation, risk assessment, and data-driven decision-making. While diffusion models have achieved remarkable success in generating static data, their direct extensions to sequential settings often fail to capture...

arXiv CS 5d ago

Integrating citizen science with experimental data uncovers how switchgrass adapts flowering by region

Integrating citizen science with experimental data uncovers how switchgrass adapts flowering by region Gaby Clark Scientific Editor Robert Egan Associate Editor In its native habitat, switchgrass flowered earlier when growing farther north. In experiments with diverse genetic samples, it flowered earlier in the south. The discrepancy wasn't a welcome sight for a research team studying how prairie grasses respond in different environments, but resolving the apparent conflict led the...

Phys.org 6d ago

Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

Announce Type: new Abstract: We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA). The primary goal is to assess whether individual samples were part of the training data of these adapted models, providing a useful auditing tool for the management of intellectual property and sensitive data. Our analysis explores the...

arXiv CS 2d ago

Revised Adaptive Immune Receptor Data in the Immune Epitope Database

The Immune Epitope Database (IEDB, iedb.org) is a freely available resource that catalogs experimentally defined immune epitopes and - if available - the immune receptors that recognize them. Currently, the IEDB records ~185,000 T cell receptors and ~5,000 B cell receptors/antibodies with experimentally verified epitope specificity. Because these receptor data were manually curated from ~3,300 references spanning decades, nomenclature inconsistencies present challenges for computational...

bioRxiv 4d ago

VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training

Announce Type: new Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories...

arXiv CS 6d ago

VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training

arXiv:2606.04708v2 Announce Type: replace Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and...

arXiv CS 5d ago

CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning

arXiv:2606.02170v1 Announce Type: new Abstract: Real-world scenarios involve massive heterogeneous structured data (e.g., tables, knowledge graphs), making effective reasoning over such diverse data increasingly important. Unified structured data question answering has emerged as a prominent research trend, aiming to answer natural language questions across different structured data types within a single framework. However, existing unified methods share a common limitation: they rely on a...

arXiv CS 8d ago