AI Safety & Ethics

Alignment, bias, regulation, and responsible AI

This Week's Best | Monthly Best | Guide | Trending

Top This Week

[2603.14267] DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
Machine Learning

[2603.14267] DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization

Abstract page for arXiv paper 2603.14267: DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and ...

arXiv - AI · 4 min ·
[2601.22440] AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
Llms

[2601.22440] AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations

Abstract page for arXiv paper 2601.22440: AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Value...

arXiv - AI · 4 min ·
[2601.13622] CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models
Llms

[2601.13622] CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models

Abstract page for arXiv paper 2601.13622: CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language...

arXiv - AI · 3 min ·

All Content

[2603.00004] Bug Severity Prediction in Software Projects Using Supervised Machine Learning Models
Machine Learning

[2603.00004] Bug Severity Prediction in Software Projects Using Supervised Machine Learning Models

Abstract page for arXiv paper 2603.00004: Bug Severity Prediction in Software Projects Using Supervised Machine Learning Models

arXiv - Machine Learning · 4 min ·
[2603.01751] Shape-Interpretable Visual Self-Modeling Enables Geometry-Aware Continuum Robot Control
Machine Learning

[2603.01751] Shape-Interpretable Visual Self-Modeling Enables Geometry-Aware Continuum Robot Control

Abstract page for arXiv paper 2603.01751: Shape-Interpretable Visual Self-Modeling Enables Geometry-Aware Continuum Robot Control

arXiv - Machine Learning · 4 min ·
[2603.02064] Never Saddle for Reparameterized Steepest Descent as Mirror Flow
Machine Learning

[2603.02064] Never Saddle for Reparameterized Steepest Descent as Mirror Flow

Abstract page for arXiv paper 2603.02064: Never Saddle for Reparameterized Steepest Descent as Mirror Flow

arXiv - Machine Learning · 3 min ·
[2603.02005] Mitigating topology biases in Graph Diffusion via Counterfactual Intervention
Machine Learning

[2603.02005] Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

Abstract page for arXiv paper 2603.02005: Mitigating topology biases in Graph Diffusion via Counterfactual Intervention

arXiv - Machine Learning · 4 min ·
[2603.02002] MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction Potentials
Machine Learning

[2603.02002] MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction Potentials

Abstract page for arXiv paper 2603.02002: MatRIS: Toward Reliable and Efficient Pretrained Machine Learning Interaction Potentials

arXiv - Machine Learning · 4 min ·
[2603.01508] The Sentience Readiness Index: Measuring National Preparedness for the Possibility of Artificial Sentience
Ai Safety

[2603.01508] The Sentience Readiness Index: Measuring National Preparedness for the Possibility of Artificial Sentience

Abstract page for arXiv paper 2603.01508: The Sentience Readiness Index: Measuring National Preparedness for the Possibility of Artificia...

arXiv - AI · 4 min ·
[2603.01907] Efficient RLVR Training via Weighted Mutual Information Data Selection
Llms

[2603.01907] Efficient RLVR Training via Weighted Mutual Information Data Selection

Abstract page for arXiv paper 2603.01907: Efficient RLVR Training via Weighted Mutual Information Data Selection

arXiv - Machine Learning · 4 min ·
[2603.01305] AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
Machine Learning

[2603.01305] AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models

Abstract page for arXiv paper 2603.01305: AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models

arXiv - AI · 4 min ·
[2603.01246] Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
Llms

[2603.01246] Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders

Abstract page for arXiv paper 2603.01246: Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders

arXiv - AI · 4 min ·
[2603.01526] Scalable Multi-Task Low-Rank Model Adaptation
Machine Learning

[2603.01526] Scalable Multi-Task Low-Rank Model Adaptation

Abstract page for arXiv paper 2603.01526: Scalable Multi-Task Low-Rank Model Adaptation

arXiv - Machine Learning · 4 min ·
[2603.01501] GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
Llms

[2603.01501] GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control

Abstract page for arXiv paper 2603.01501: GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control

arXiv - Machine Learning · 3 min ·
[2603.01367] DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking
Machine Learning

[2603.01367] DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking

Abstract page for arXiv paper 2603.01367: DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking

arXiv - Machine Learning · 4 min ·
[2603.01124] ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models
Llms

[2603.01124] ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models

Abstract page for arXiv paper 2603.01124: ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models

arXiv - AI · 4 min ·
[2603.01304] Nonconvex Latent Optimally Partitioned Block-Sparse Recovery via Log-Sum and Minimax Concave Penalties
Ai Safety

[2603.01304] Nonconvex Latent Optimally Partitioned Block-Sparse Recovery via Log-Sum and Minimax Concave Penalties

Abstract page for arXiv paper 2603.01304: Nonconvex Latent Optimally Partitioned Block-Sparse Recovery via Log-Sum and Minimax Concave Pe...

arXiv - Machine Learning · 3 min ·
[2603.01096] Unified Vision-Language Modeling via Concept Space Alignment
Llms

[2603.01096] Unified Vision-Language Modeling via Concept Space Alignment

Abstract page for arXiv paper 2603.01096: Unified Vision-Language Modeling via Concept Space Alignment

arXiv - Machine Learning · 4 min ·
[2603.01292] Integrating LTL Constraints into PPO for Safe Reinforcement Learning
Robotics

[2603.01292] Integrating LTL Constraints into PPO for Safe Reinforcement Learning

Abstract page for arXiv paper 2603.01292: Integrating LTL Constraints into PPO for Safe Reinforcement Learning

arXiv - Machine Learning · 3 min ·
[2603.01028] Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features
Machine Learning

[2603.01028] Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features

Abstract page for arXiv paper 2603.01028: Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Fea...

arXiv - AI · 3 min ·
[2603.01006] AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
Machine Learning

[2603.01006] AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

Abstract page for arXiv paper 2603.01006: AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

arXiv - Machine Learning · 4 min ·
[2603.01001] Data-Free PINNs for Compressible Flows: Mitigating Spectral Bias and Gradient Pathologies via Mach-Guided Scaling and Hybrid Convolutions
Machine Learning

[2603.01001] Data-Free PINNs for Compressible Flows: Mitigating Spectral Bias and Gradient Pathologies via Mach-Guided Scaling and Hybrid Convolutions

Abstract page for arXiv paper 2603.01001: Data-Free PINNs for Compressible Flows: Mitigating Spectral Bias and Gradient Pathologies via M...

arXiv - AI · 4 min ·
[2603.01013] Feature-Weighted Maximum Representative Subsampling
Ai Safety

[2603.01013] Feature-Weighted Maximum Representative Subsampling

Abstract page for arXiv paper 2603.01013: Feature-Weighted Maximum Representative Subsampling

arXiv - Machine Learning · 4 min ·
Previous Page 25 Next

Related Topics

Machine Learning Large Language Models Generative AI Natural Language Processing Computer Vision Robotics & Embodied AI

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime