4 papers · 1 filter
Scaling Reinforcement Learning for Diffusion Models via Velocity Matching
Jaemoo Choi, Wei Guo, Yuchen Zhu +4
Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing methods largely inherit policy-gradie…
Thinking with Anchors: Grounded and Efficient Document Reasoning
Sichen Zhu, Yuchen Zhu, Wenzhuo Xu +13
Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reason jointly about region seman…
LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
Shufan Li, Yuchen Zhu, Jiuxiang Gu +6
Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generati…
Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images
Sichen Zhu, Yuchen Zhu, Molei Tao +1
Spatial Transcriptomics (ST) allows a high-resolution measurement of RNA sequence abundance by systematically connecting cell morphology depicted in Hematoxylin and Eosin (H&E) sta…