7 papers
Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage
Peiyu Yu, Suraj Kothawade, Sirui Xie +2
Most post-training methods for text-to-image samplers focus on model weights: either fine-tuning the backbone for alignment or distilling it for few-step efficiency. We take a diff…
"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihood
Peiyu Yu, Dinghuai Zhang, Hengzhi He +10
Noise Contrastive Estimation (NCE) has fueled major breakthroughs in representation learning and generative modeling. Yet a long-standing challenge remains: accurately estimating r…
EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
Tianyu Chen, Yasi Zhang, Zhi Zhang +13
Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images…
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
Yasi Zhang, Peiyu Yu, Yaxuan Zhu +4
Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the in…
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
Haozhe Zhao, Xiaojian Ma, Liang Chen +7
This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to addr…
DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting
Eric Hanchen Jiang, Zhi Zhang, Dinghuai Zhang +9
Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world…