paper-with-me

홈 › Papers

Calibrating Generative Models to Feature Distributions with MMD Finetuning

2026-06-17 · Nathaniel L. Diamant, Brian L. Trippe arxiv

Generative models can produce individually plausible samples while deviating substantially from a target set in the distribution of key features. For example, a model pretrained on broad drug-like chemical space may generate molecules whose molecular features differ from those of a therapeutic class of interest, such as known antibiotics. Correcting such distributional miscalibration is challenging: direct finetuning on the target set can overfit and does not control which features are matched. To fill this gap, we introduce kernel Calibrating Generative Models (kCGM). kCGM minimizes a maximum mean discrepancy (MMD) between generated and target feature distributions using an unbiased score-function estimator, with KL regularization to remain close to the pretrained model. On a target set of 174 antibiotics, direct finetuning sacrifices chemical validity for feature-distribution matching, whereas kCGM improves target feature matching while increasing validity. We further demonstrate kCGM in protein and DNA generation tasks, showing it can adapt autoregressive, continuous-space diffusion, and discrete diffusion models using only feature-level supervision. Code is available at https://github.com/smithhenryd/cgm.

📄 PDF Abstract BibTeX arXiv:2606.19496

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Judging with Confidence: Calibrating Autoraters to Preference Distributions

2025-09-30 · Zhuohang Li, Xiaowei Li, Chengyu Huang, Guowang Li 외 arxiv

The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limited by a foundational issue: they are trai…

Reinforcement Learning

Long Horizon Temperature Scaling

2023-02-07 · Andy Shih, Dorsa Sadigh, Stefano Ermon

Temperature scaling is a popular technique for tuning the sharpness of a model distribution. It is used extensively for sampling likely generations and calibrating model uncertainty, and even features as a controllable p…

Multiple-choice

Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling

2022-04-07 · Ran Tao, Han Zhang, Yutong Zheng, Marios Savvides

In recent works, utilizing a deep network trained on meta-training set serves as a strong baseline in few-shot learning. In this paper, we move forward to refine novel-class features by finetuning a trained deep network.…

Few-Shot Learning

Sports Camera Calibration via Synthetic Data

2018-10-25 · Jianhui Chen, James J. Little

Calibrating sports cameras is important for autonomous broadcasting and sports analysis. Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data. First, we develo…

Camera CalibrationGenerative Adversarial NetworkSports Analytics

Calibrating Verbalized Probabilities for Large Language Models

2024-10-09 · Cheng Wang, Gyuri Szarvas, Georges Balazs, Pavel Danchenko 외

Calibrating verbalized probabilities presents a novel approach for reliably assessing and leveraging outputs from black-box Large Language Models (LLMs). Recent methods have demonstrated improved calibration by applying …