123,304Total entries

60Added by human

123,244Found by agent

13Categories

Knowledge catalogue

Search: “privacy”

3,028 results

Safety

Knowledge Distillation Must Account for What It Loses

DGX agent

arXiv:2604.25110v1 Announce Type: new Abstract: This position paper argues that knowledge distillation must account for what it loses: student models should be judged not only by retained task scores,

safetyarxiv-cs-lg

29 Apr 2026

Agents

MCP now available in Thoth

DGX agent

Thoth, a local-first desktop AI assistant, now supports Model Context Protocol (MCP) tools, allowing users to run it fully locally with Ollama or integrate frontier APIs as needed. The application pri

Search: “privacy”

Knowledge Distillation Must Account for What It Loses

MCP now available in Thoth

Subspace Optimization for Efficient Federated Learning under Heterogeneous Data

Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health

What are people using for low-latency autocomplete in production? [P]

What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective

A Large-Scale, Cross-Disciplinary Corpus of Systematic Reviews

An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code

BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Decoupling Wavelet Sub-bands for Single Source Domain Generalization in Fundus Image Segmentation

Designing Robots to Support Parent-Child Connections: Opportunities Through Robot-Mediated Communication

Does Machine Unlearning Preserve Clinical Safety? A Risk Analysis for Medical Image Classification

EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce

Failure-Centered Runtime Evaluation for Deployed Trilingual Public-Space Agents

FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection

High-Dimensional Private Linear Regression with Optimal Rates

I’ve been saying this for over a year now: Frontier models are fantastic, but the real future is frontier-level models (in every way) runnin…

Machine Learning for Network Attacks Classification and Statistical Evaluation of Adversarial Learning Methodologies for Synthetic Data Generation

Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact

Securely send first-party conversion signals with Snapchat Conversions API on Databricks Marketplace

STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator

Supporting Family-School Partnerships with Robot-Facilitated Home-Based Activities

Tessera: Secure, Near-Line-Rate Weight Streaming for UMA Edge Accelerators

The great American data center divide

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Transferable Human Mobility Network Reconstruction with neuroGravity

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work

An Artifact-based Agent Framework for Adaptive and Reproducible Medical Image Processing

An Interdisciplinary and Cross-Task Review on Missing Data Imputation

FeatEHR-LLM: Leveraging Large Language Models for Feature Engineering in Electronic Health Records

FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet

FETS Benchmark: Foundation Models Outperform Dataset-specific Machine Learning in Energy Time Series Forecasting

TabSCM: A practical Framework for Generating Realistic Tabular Data

Using Embedding Models to Improve Probabilistic Race Prediction

Very cool analysis of the submissions to a major management journal that shows how much the system of science, built for humans, is under st…

ViFiCon: Vision and Wireless Association Via Self-Supervised Contrastive Learning

Experian takes consumer financial guidance to the next level with AI-powered virtual assistant

Accurate predictive model of band gap with selected important features based on explainable machine learning

Architectures for Robust Self-Organizing Energy Systems under Information and Control Constraints

Building my own Agentic Environment from scratch, in Go, for sandbox-per-agent usage

Enabling and Inhibitory Pathways of University Students' Willingness to Disclose AI Use: A Cognition-Affect-Conation Perspective

Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation

Federated Co-tuning Framework for Large and Small Language Models

Great launches recently. Time for temperature check! Based on what you've read, which of these 2 are you going to be using as your 'main' co…

Human Presence Detection via Wi-Fi Range-Filtered Doppler Spectrum on Commodity Laptops

Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs