127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “research”

39,588 results

Research

Algorithmic stability via ensembling

DGX agent

arXiv:2609.10428v1 Announce Type: cross Abstract: Algorithmic stability refers to the property of an algorithm being insensitive to perturbations of the input data, where the type of perturbation may

researcharxiv-cs-lg

10 Sept 2026

Research

Search: “research”

Algorithmic stability via ensembling

An Explainable Machine Learning Framework for Predicting Blood-Brain Barrier Permeability Using Molecular Descriptors

AstroSpecLM: A Spectrum-Language Model for Evidence-Grounded Astronomical Spectral Analysis

Auditable Emergency Triage for Maternal and Newborn Care in India

AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering

Beyond Contact Sensors: Deep learning with Pseudo-Labeling for remote Photoplethysmography

Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval

Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis

Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Beyond Weak Labels: Prompt-Guided Local Refinement for Weakly Supervised Water Segmentation in High-Resolution Multispectral Imagery

Bilevel Planning with Learned Symbolic Abstractions from Interaction Data

BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents

CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription

Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning

CAST: Canonical Approximate Schur Tree for Approximate Cholesky on Graphs

Central Dogma Transformer II: An AI Microscope for Understanding Cellular Regulatory Mechanisms

Characterizing Language Generation in the Limit: Finite Witnesses and a Separation-Width Hierarch

CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification

Coastal Environment Generation with HoloOcean

CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification

ConvMem: Convolutional Memory for Long-Context Reasoning

CougarTail & CUB: A General-Purpose Mast and Central Utility Board for Cylindrical Underwater Enclosures

Critical initialization destabilizes higher input derivatives in wide scalar-input networks

CriticGen: Generation-Aware Evaluation as Actionable Feedback

Cyber-Financial Contagion: Modeling the Propagation of an AI Vendor Compromise Through the Banking System

Dead Directions: Geometric Singular Learning

Decision Transformer for UAV-Mounted RIS-Assisted Dynamic D2D Communications

DensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision

Design and Attitude Control of an Underwater Quadruped Robot

Dimensionality Reduction for Hyperspectral Image Classification

Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow Prediction

Distillation of Synthetic Data for Time Series Foundation Models

Distilling Image Prototypes for Guided Test-Time Adaptation

Diverse Instance Generation via Diffusion Models for Enhanced Few-Shot Object Detection in Remote Sensing Images

DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation

Dynamical Non-compensatory Multidimensional IRT Model Using Variational Approximation

Efficient Graph Neural Networks for Multicarrier Wideband Hybrid Beamforming Optimization

Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation

Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization

Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports

Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence

Evidential-Based Higher-Order Set Argumentation Framework

EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering

Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings