7 papers
Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization
Yifu Luo, Haoyuan Sun, Xinhao Hu +12
Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is h…
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Zunhai Su, Hengyuan Zhang, Wei Wu +24
As the foundational architecture of modern machine learning, Transformers have driven remarkable progress across diverse AI domains. Despite their transformative impact, a persiste…
XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
Zunhai Su, Weihao Ye, Hansen Feng +5
Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to d…
Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
Yifu Luo, Xinhao Hu, Keyu Fan +6
Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or aut…
XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression
Zunhai Su, Weihao Ye, Hansen Feng +5
Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong stream…
Hear-Your-Click: Interactive Object-Specific Video-to-Audio Generation
Yingshan Liang, Keyu Fan, Zhicheng Du +5
Video-to-audio (V2A) generation shows great potential in fields such as film production. Despite significant advances, current V2A methods relying on global video information strug…