15 papers
TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
Xinyu Wei, Jinrui Zhang, Zeqing Wang +4
The rapid advancements of Text-to-Image (T2I) models have ushered in a new phase of AI-generated content, marked by their growing ability to interpret and follow user instructions.…
SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
Yankai Yang, Yancheng Long, Wei Chen +7
Recent online reinforcement learning has substantially improved image editing quality. However, existing Flow-GRPO-style methods usually rely on a single whole-image reward, which…
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
Yankai Yang, Yancheng Long, Hongyang Wei +12
Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as i…
Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
Zihan Su, Hongyang Wei, Kangrui Cen +4
Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding an…
VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?
Zeqing Wang, Xinyu Wei, Bairui Li +5
The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making the existing benchmarks increasing…
SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
Yancheng Long, Yankai Yang, Hongyang Wei +12
Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Exi…