Summary of Self-correcting Self-consuming Loops For Generative Model Training, by Nate Gillman et al.
Self-Correcting Self-Consuming Loops for Generative Model Trainingby Nate Gillman, Michael Freeman, Daksh Aggarwal, Chia-Hong Hsu,…
Self-Correcting Self-Consuming Loops for Generative Model Trainingby Nate Gillman, Michael Freeman, Daksh Aggarwal, Chia-Hong Hsu,…
Group Distributionally Robust Dataset Distillation with Risk Minimizationby Saeed Vahidian, Mingyu Wang, Jianyang Gu, Vyacheslav…
CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelinesby Chao Pang, Xinzhuo Jiang, Nishanth Parameshwar…
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Databy Yvonne Zhou,…
Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learningby Zihan Ding, Amy…
SynthVision – Harnessing Minimal Input for Maximal Output in Computer Vision Models using Synthetic Image…
SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approachby Tianshi Wang,…
SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Trackingby Atharva Kulkarni, Bo-Hsiang…
Enhancing crop classification accuracy by synthetic SAR-Optical data generation using deep learningby Ali Mirzaei, Hossein…
On the Exploitation of DCT-Traces in the Generative-AI Domainby Orazio Pontorno, Luca Guarnera, Sebastiano BattiatoFirst…