A 1.3B-parameter rectified flow transformer is the first generative foundation model for chest radiograph synthesis at billion-parameter scale, producing images indistinguishable from real ones to experts.
arXiv preprint arXiv:2012.09092 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
PlayWorld learns high-fidelity robot world models from unsupervised self-play, producing physically consistent video predictions that outperform models trained on human data and enabling 65% better real-world policy performance via model-based RL.
Non-parametric closed-form bounds on counterfactual MDP transitions across compatible causal models, supporting robust policy optimization under interval uncertainty.
CRDA augments regression datasets by generating counterfactual samples from invariant residuals, cutting MLP MSE by 22.9% and XGBoost MSE by 6.4% on average across benchmarks.
Counterfactual transport flows enable conservative, instance-specific trajectory refinement in offline RL by constructing local preference pairs in latent space from offline data and learning refinement directions controlled by a strength parameter.
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
citing papers explorer
-
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
A 1.3B-parameter rectified flow transformer is the first generative foundation model for chest radiograph synthesis at billion-parameter scale, producing images indistinguishable from real ones to experts.
-
PlayWorld: Learning Robot World Models from Autonomous Play
PlayWorld learns high-fidelity robot world models from unsupervised self-play, producing physically consistent video predictions that outperform models trained on human data and enabling 65% better real-world policy performance via model-based RL.
-
Robust Counterfactual Inference in Markov Decision Processes
Non-parametric closed-form bounds on counterfactual MDP transitions across compatible causal models, supporting robust policy optimization under interval uncertainty.
-
Counterfactual Residual Data Augmentation for Regression
CRDA augments regression datasets by generating counterfactual samples from invariant residuals, cutting MLP MSE by 22.9% and XGBoost MSE by 6.4% on average across benchmarks.
-
Counterfactual Transport Flows for Offline Conservative Trajectory Refinement
Counterfactual transport flows enable conservative, instance-specific trajectory refinement in offline RL by constructing local preference pairs in latent space from offline data and learning refinement directions controlled by a strength parameter.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.