127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

All entries

94,811 results

Safety

Data Deletion Can Help in Adaptive RL

DGX agent

arXiv:2605.00298v1 Announce Type: new Abstract: Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Mark

safetyarxiv-cs-lg

4 May 2026

Safety

All entries

Data Deletion Can Help in Adaptive RL

Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations

Decentralized Proximal Stochastic Gradient Langevin Dynamics

Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors

Deep Kernel Learning for Stratifying Glaucoma Trajectories

Deepfakes: we need to re-think the concept of 'real' images

DeGenTWeb: A First Look at LLM-dominant Websites

Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds

Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling

DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion

Diffusion Models are Secretly Zero-Shot 3DGS Harmonizers

Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance

Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media

Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces

Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers

Disentangled Control of Multi-Agent Systems

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment

Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty

Distance metric learning for conditional anomaly detection

Diversity in Large Language Models under Supervised Fine-Tuning

DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets

Do Open-Loop Metrics Predict Closed-Loop Driving? A Cross-Benchmark Correlation Study of NAVSIM and Bench2Drive

Doubly robust identification of treatment effects from multiple environments

DPU or GPU for Accelerating Neural Networks Inference -- Why not both? Split CNN Inference

Driving with A Thousand Faces: A Benchmark for Closed-Loop Personalized End-to-End Autonomous Driving

Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction

Dynamics-Encoded Deep Learning for Robust System Identification and Parameter Estimation

E^2DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation

EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure

Efficient Finite Initialization with Partial Norms for Tensorized Neural Networks and Tensor Networks Algorithms

Efficient Mutation Testing of Quantum Machine Learning Models

Efficient Spatio-Temporal Vegetation Pixel Classification with Vision Transformers

EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement

Elimination Templates in Macaulay2

Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer

Escaping Mode Collapse in LLM Generation via Geometric Regulation

Estimating LLM Grading Ability and Response Difficulty in Automatic Short Answer Grading via Item Response Theory

Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics

Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game

Event-based Civil Infrastructure Visual Defect Detection: ev-CIVIL Dataset and Benchmark

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

Exploring LLM biases to manipulate AI search overview

Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection

Exploring the System 1 Thinking Capability of Large Reasoning Models

Fair Dataset Distillation via Cross-Group Barycenter Alignment

Fairness of Classifiers in the Presence of Constraints between Features

Faithful Extreme Image Rescaling with Learnable Reversible Transformation and Semantic Priors