Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards Paper • 2610.02967 • Published 12 days ago • 38
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations Paper • 2610.00994 • Published 13 days ago • 31
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 15 days ago • 131
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning Paper • 2610.02824 • Published 12 days ago • 33
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces Paper • 2609.40362 • Published 14 days ago • 40
Scaling and Distilling Text Embeddings for Better Diffusibility Paper • 2610.01016 • Published 13 days ago • 58
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 16 days ago • 394
FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching Paper • 2609.35673 • Published 16 days ago • 34
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published 15 days ago • 138
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets Paper • 2609.37775 • Published 15 days ago • 26
AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation Paper • 2609.35530 • Published 16 days ago • 22