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

[2603.00883] Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact
Llms

[2603.00883] Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact

Abstract page for arXiv paper 2603.00883: Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact

arXiv - Machine Learning · 3 min ·
[2603.00856] PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems
Llms

[2603.00856] PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems

Abstract page for arXiv paper 2603.00856: PARCER as an Operational Contract to Reduce Variance, Cost, and Risk in LLM Systems

arXiv - AI · 4 min ·
[2603.00742] To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters
Machine Learning

[2603.00742] To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters

Abstract page for arXiv paper 2603.00742: To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters

arXiv - Machine Learning · 4 min ·
[2603.00589] AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution
Machine Learning

[2603.00589] AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution

Abstract page for arXiv paper 2603.00589: AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution

arXiv - AI · 4 min ·
[2603.00574] Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation
Machine Learning

[2603.00574] Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation

Abstract page for arXiv paper 2603.00574: Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation

arXiv - AI · 4 min ·
[2603.00483] RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
Machine Learning

[2603.00483] RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment

Abstract page for arXiv paper 2603.00483: RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment

arXiv - AI · 4 min ·
[2603.00488] Dynamic Spatio-Temporal Graph Neural Network for Early Detection of Pornography Addiction in Adolescents Based on Electroencephalogram Signals
Machine Learning

[2603.00488] Dynamic Spatio-Temporal Graph Neural Network for Early Detection of Pornography Addiction in Adolescents Based on Electroencephalogram Signals

Abstract page for arXiv paper 2603.00488: Dynamic Spatio-Temporal Graph Neural Network for Early Detection of Pornography Addiction in Ad...

arXiv - Machine Learning · 4 min ·
[2603.00454] Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training
Llms

[2603.00454] Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

Abstract page for arXiv paper 2603.00454: Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

arXiv - Machine Learning · 3 min ·
[2603.00431] Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models
Machine Learning

[2603.00431] Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimodal Models

Abstract page for arXiv paper 2603.00431: Taxonomy-Aware Representation Alignment for Hierarchical Visual Recognition with Large Multimod...

arXiv - AI · 4 min ·
[2603.00429] Personalities at Play: Probing Alignment in AI Teammates
Llms

[2603.00429] Personalities at Play: Probing Alignment in AI Teammates

Abstract page for arXiv paper 2603.00429: Personalities at Play: Probing Alignment in AI Teammates

arXiv - AI · 4 min ·
[2603.00318] AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement
Robotics

[2603.00318] AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement

Abstract page for arXiv paper 2603.00318: AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement

arXiv - AI · 3 min ·
[2603.00306] When does Chain-of-Thought Help: A Markovian Perspective
Machine Learning

[2603.00306] When does Chain-of-Thought Help: A Markovian Perspective

Abstract page for arXiv paper 2603.00306: When does Chain-of-Thought Help: A Markovian Perspective

arXiv - Machine Learning · 3 min ·
[2603.00200] LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance
Robotics

[2603.00200] LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance

Abstract page for arXiv paper 2603.00200: LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance

arXiv - AI · 3 min ·
[2603.00188] Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression
Llms

[2603.00188] Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression

Abstract page for arXiv paper 2603.00188: Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression

arXiv - Machine Learning · 4 min ·
[2603.00166] Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?
Machine Learning

[2603.00166] Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

Abstract page for arXiv paper 2603.00166: Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

arXiv - AI · 3 min ·
[2603.00144] Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
Machine Learning

[2603.00144] Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation

Abstract page for arXiv paper 2603.00144: Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation

arXiv - AI · 3 min ·
[2603.00140] Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
Machine Learning

[2603.00140] Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion

Abstract page for arXiv paper 2603.00140: Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Im...

arXiv - Machine Learning · 3 min ·
[2603.00131] Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems
Llms

[2603.00131] Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems

Abstract page for arXiv paper 2603.00131: Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems

arXiv - AI · 3 min ·
[2603.00121] Graph-theoretic Agreement Framework for Multi-agent LLM Systems
Llms

[2603.00121] Graph-theoretic Agreement Framework for Multi-agent LLM Systems

Abstract page for arXiv paper 2603.00121: Graph-theoretic Agreement Framework for Multi-agent LLM Systems

arXiv - AI · 4 min ·
[2603.00078] Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction
Ai Safety

[2603.00078] Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction

Abstract page for arXiv paper 2603.00078: Alignment Is Not Enough: A Relational Framework for Moral Standing in Human-AI Interaction

arXiv - AI · 4 min ·
Previous Page 26 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