5 papers
WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning
Ryan Xu, Atlas Zhao, David Bao +1
Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectorie…
Eevee: Towards Close-up High-resolution Video-based Virtual Try-on
Jianhao Zeng, Yancheng Bai, Ruidong Chen +7
Video virtual try-on technology provides a cost-effective solution for creating marketing videos in fashion e-commerce. However, its practical adoption is hindered by two critical…
Semantic Context Matters: Improving Conditioning for Autoregressive Models
Dongyang Jin, Ryan Xu, Jianhao Zeng +4
Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared t…
SCALAR: Scale-wise Controllable Visual Autoregressive Learning
Ryan Xu, Dongyang Jin, Yancheng Bai +4
Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation…
Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages
William Zhang, Maria Leon, Ryan Xu +10
Node-based programming languages are increasingly popular in media arts coding domains. These languages are designed to be accessible to users with limited coding experience, allow…