Statistical attribute alignment for black-box generative AI via output post-processing
stat.ME, cs.AI, cs.LG, math.ST, stat.TH
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/deepinsight/insightface
Terminology
Sources
- Harnessing Synthetic Data from Generative AI for Statistical Inference
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
- Constitutional AI: Harmlessness from AI Feedback
- General Synthetic-Powered Inference
- On the Opportunities and Risks of Foundation Models
- DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models
- Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
- On the Partition Function and Random Maximum A-Posteriori Perturbations
- AI Alignment: A Comprehensive Survey
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- A Distributional Approach to Controlled Text Generation
- Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator
- Machine Learning for Synthetic Data Generation: A Review
- Artificial Intelligence Index Report 2025
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data
- Augmenting medical image classifiers with synthetic data from latent diffusion models
- Finetuning Text-to-Image Diffusion Models for Fairness
- Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models
- Qwen-Image Technical Report
Related papers
- Doubly robust inference via calibration
- Bayesian Empirical Bayes: Simultaneous Inference from Probabilistic Symmetries
- Optimal Watermark Localization in Mixed-Source Large Language Model Texts
- Flexible Nonparametric Inference for Causal Effects under the Front-Door Model
- A Greedy PDE Router for Blending Neural Operators and Classical Methods
- Policy Learning with Weak Signals