New research explores generative models for physics, efficiency, and calibration
ByPulseAugur Editorial·[9 sources]·
Several new research papers explore advancements in generative models, focusing on statistical validation, efficient training methods, and calibration techniques. One paper introduces Midpoint Generative Models (MGM) for one-step generation, while another proposes a parameter-efficient framework using controlled vector fields. Additionally, research is being done on aligning few-step generative models and calibrating them to meet distributional constraints, with applications in areas like robotics and protein design.
AI
IMPACT
These papers introduce novel methods for training, validating, and aligning generative models, potentially improving their efficiency and reliability across various applications.
RANK_REASON
Multiple arXiv papers published on generative models and related techniques.
arXiv:2502.04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, bi…
arXiv cs.LG
TIER_1English(EN)·Shashaank Aiyer, Yishay Mansour, Shay Moran, Han Shao·
arXiv:2604.05324v2 Announce Type: replace Abstract: Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance me…
arXiv:2503.07154v3 Announce Type: replace-cross Abstract: Generative pre-training is often framed through a false dichotomy between autoregressive models for discrete signals and diffusion models for continuous signals. We argue that the dichotomy is false because it conflates mo…
arXiv cs.LG
TIER_1English(EN)·Sascha Diefenbacher, Sofia Palacios Schweitzer, Gregor Kasieczka·
arXiv:2605.30453v1 Announce Type: cross Abstract: Generative machine learning has become an essential tool in theoretical and experimental physics, especially in the context of fast surrogates and density estimators. In this work, we first introduce the underlying framework of mo…
arXiv cs.LG
TIER_1English(EN)·Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy, Dmitry V. Dylov, Alexander Korotin·
arXiv:2605.29920v1 Announce Type: new Abstract: We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interpolation: when the two endpoint distributions coincid…
We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and learned scalar controls. Instead of learning an unconstrained high-dimensional vector field, our framew…
arXiv cs.AI
TIER_1English(EN)·Jaewoo Lee, Hyeongyu Kang, Dohyun Kim, Kyuil Sim, Woocheol Shin, Minsu Kim, Taeyoung Yun, Jeongjae Lee, Sanghyeok Choi, Tabitha Edith Lee, Jongchul Ye, Jinkyoo Park·
arXiv:2605.26552v1 Announce Type: cross Abstract: Aligning a few-step generative model is challenging, since existing alignment frameworks typically rely on restrictive assumptions: a tractable likelihood, a specific ODE/SDE solver, or a particular model family. We introduce FAV,…
arXiv:2606.00425v1 Announce Type: cross Abstract: Moment conditions are widely used to identify parameters in models where the full likelihood is either unknown or intentionally left unspecified. Empirical likelihood methods address this problem by assigning probability weights t…
arXiv stat.ML
TIER_1English(EN)·Henry D. Smith, Nathaniel L. Diamant, Brian L. Trippe·
arXiv:2510.10020v4 Announce Type: replace Abstract: Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution, such as the fraction of generations in a given class, deviate from desired values. We frame calibration as a constrained optimi…