Simplifying and Improving On-Policy Distillation for Few-Step Diffusion Paper • 2610.18472 • Published 4 days ago • 22
Vela: User Behavior as Supervision Sparks LLM Intelligence Paper • 2610.14709 • Published 7 days ago • 77
Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment Paper • 2609.35291 • Published 19 days ago • 26
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 17 days ago • 317
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards Paper • 2610.02967 • Published 15 days ago • 42
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations Paper • 2610.00994 • Published 16 days ago • 32
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Paper • 2609.38169 • Published 18 days ago • 131
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning Paper • 2610.02824 • Published 15 days ago • 33
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces Paper • 2609.40362 • Published 17 days ago • 40
Scaling and Distilling Text Embeddings for Better Diffusibility Paper • 2610.01016 • Published 16 days ago • 58
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 19 days ago • 396
FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching Paper • 2609.35673 • Published 19 days ago • 35