Adversarial Flow Models
Paper • 2511.22475 • Published • 24
dailypaper
-
-
DiP: Taming Diffusion Models in Pixel Space
Paper • 2511.18822 • Published • 29 -
Asking like Socrates: Socrates helps VLMs understand remote sensing images
Paper • 2511.22396 • Published • 5 -
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Paper • 2512.05591 • Published • 17 -
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
Paper • 2512.00473 • Published • 27 -
SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning
Paper • 2512.03244 • Published • 17 -
TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
Paper • 2512.08153 • Published • 8 -
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Paper • 2512.11749 • Published • 39 -
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Paper • 2512.13607 • Published • 38 -
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Paper • 2512.16636 • Published • 26 -
Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
Paper • 2512.21625 • Published • 4 -
Self-Evaluation Unlocks Any-Step Text-to-Image Generation
Paper • 2512.22374 • Published • 17 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 230 -
GARDO: Reinforcing Diffusion Models without Reward Hacking
Paper • 2512.24138 • Published • 30 -
Boosting Latent Diffusion Models via Disentangled Representation Alignment
Paper • 2601.05823 • Published • 17 -
Your Group-Relative Advantage Is Biased
Paper • 2601.08521 • Published • 158 -
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
Paper • 2601.10332 • Published • 31