Adversarial Flow Models
Paper
•
2511.22475
•
Published
•
22
dailypaper
-
-
DiP: Taming Diffusion Models in Pixel Space
Paper • 2511.18822 • Published • 28 -
Asking like Socrates: Socrates helps VLMs understand remote sensing images
Paper • 2511.22396 • Published • 4 -
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Paper • 2512.05591 • Published • 16 -
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
Paper • 2512.00473 • Published • 25 -
SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning
Paper • 2512.03244 • Published • 16 -
TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
Paper • 2512.08153 • Published • 6 -
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Paper • 2512.11749 • Published • 36 -
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Paper • 2512.13607 • Published • 26 -
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Paper • 2512.16636 • Published • 25 -
Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
Paper • 2512.21625 • Published • 3 -
Self-Evaluation Unlocks Any-Step Text-to-Image Generation
Paper • 2512.22374 • Published • 2