Generative Modeling
PulseAugur coverage of Generative Modeling — every cluster mentioning Generative Modeling across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New arXiv Paper Links Physics Concepts to Machine Learning Applications
A new review paper published on arXiv explores the deep connections between control theory, optimal transport, probabilistic inference, non-equilibrium thermodynamics, and machine learning. The paper highlights how thes…
-
AI model generates forest canopies, reproducing 'crown shyness' phenomenon
Researchers have developed a novel flow-matching model capable of generating entire forest canopies, specifically addressing the phenomenon of crown shyness where tree crowns avoid touching. This joint generation approa…
-
Diffusion models research tackles outliers, efficiency, and theory · 10 sources tracked
Recent research explores advancements in diffusion models, focusing on improving their robustness, efficiency, and theoretical understanding. Papers address challenges like outlier data in inverse problems, scaling rein…
-
New Joint Flow Matching Generative Model Predicts Cell Morphing Effects
Researchers have developed a new generative modeling technique called Joint Flow Matching to predict the effects of chemical compounds on cells. This method allows for continuous dose-conditioning, unlike previous appro…
-
New research explores scaling laws and training strategies for diffusion image models
Researchers have published several papers exploring advancements in diffusion models for image generation. One study, "Abra: Scaling Diffusion Image Training," details a systematic analysis of scaling laws for text-to-i…
-
New DADiff framework uses diffusion models for cross-domain reinforcement learning
Researchers have introduced DADiff, a novel diffusion-based framework designed to tackle the challenge of cross-domain policy adaptation in reinforcement learning. This method addresses the dynamics mismatch between sou…
-
New monograph maps deep learning theory from approximation to emergence
A new monograph titled "From Approximation to Emergence: A Theory of Deep Learning" offers a unified, proof-oriented account of modern deep learning theory. The book traces the evolution of the field from classical conc…
-
New score matching method promises global convergence for generative models
Researchers have developed a new approach to score matching in generative modeling by utilizing reverse Fisher divergence instead of the standard forward Fisher divergence. This alternative objective demonstrates improv…
-
New L2 over Wasserstein framework enhances optimal transport for random measures
Researchers have introduced a new framework called $L^2$ over Wasserstein space to address statistical uncertainty in optimal transport. This framework extends the classical theory to random probability measures, preser…
-
Generalising maximum mean discrepancy: kernelised functional Bregman divergences
Researchers have introduced a novel framework for functional Bregman divergences, extending their application to Hilbert spaces and kernel methods. This approach leverages the properties of these spaces for more conveni…