NeurIPS 2025PastTabular & structured data
NeurIPS 2025 Workshop on Regulatable ML
RegML 2025
- Submission deadline
- Aug 30, 2025, 23:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (53)
Fetched from OpenReview (v2) on 2026-06-10.
(When) Should We Delegate AI Governance to AIs? Some Lessons from Administrative Law
A Framework for the Categorisation of General-Purpose AI Models under the EU AI Act
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
AI, Climate, and Transparency: Operationalizing and Improving the AI Act
Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face
Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
Auditable AI Literacy Interventions: Embedding Regulatory Principles into Higher Education
Beware! The AI Act Can Also Apply to Your AI Research Practices
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Cost Efficient Fairness Audit Under Partial Feedback
Data Forging Attacks on Cryptographic Model Certification
Debugging Concept Bottleneck Models through Removal and Retraining
Deepfakes in Political Manipulation: Evaluating Risks Under the AI Act
Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings
Do AI Companies Make Good on Voluntary Commitments to the White House?
Emergency Response Measures for Catastrophic Risk
Empirical Evidence for Alignment Faking in a Small LLM and Prompt-Based Mitigation Techniques
ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
From Proposals to Enactment: The Procedural Bottleneck in AI Safety Regulation
Harmful Information Management Practices in Frontier AI Development
HashMark: Watermarking Tabular/Synthetic Data For Machine Learning Via Cryptographic Hash Functions
How Data-Related AI Research can Support Technical Solutions for Regulatory Compliance
How do data owners say no? A case study of data consent mechanisms in web-scraped vision-language AI training datasets
Inducing Uncertainty on Open-Weight Models for Test-Time Privacy in Image Recognition
Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
It's complicated. The relationship of algorithmic fairness and non-discrimination regulations for high-risk systems in the EU AI Act
LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation
Local Differences, Global Lessons: Insights from Organisation Policies for Legislation
MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Military AI Cyber Agents (MAICAs) Constitute a Global Threat to Critical Infrastructure
On the Regulatory Potential of User Interfaces for AI Agent Governance
PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Perspective: Lessons from Cybersecurity for Biological AI Safety and Regulation
Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents
Position: Bridge the Gaps between Machine Unlearning and AI Regulation
Refining Inverse Constitutional AI for Dataset Validation under the EU AI Act
Regulating the Agency of LLM-based Agents
Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models
SemScore: Practical Explainable AI through Quantitative Methods to Measure Semantic Spuriosity
SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning
SpecEval: Evaluating Model Adherence to Behavior Specifications
Specifying Computational Compliance for AI: Blueprint for a New Research Domain
Statutory Construction and Interpretation for Artificial Intelligence
StealthEval: A Probe-Rewrite-Evaluate Workflow for Reliable Benchmarks
The Backfiring Effect of Weak AI Safety Regulation
The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
The Hidden Cost of Modeling $P(X)$: Membership Inference Attacks in Generative Text Classifiers
The Model Openness Framework: Promoting Completeness and Openness for Reproducibility, Transparency, and Usability in Artificial Intelligence
The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models
ValueDCG: Framework for Investigating Human Value Understanding Ability of Language Models through Discriminator-Critique Gap