3 papers
cs.CV2025
Fast Video Generation with Sliding Tile Attention
Peiyuan Zhang, Yongqi Chen, Runlong Su +4
Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video…
cs.NI2025
The Effect of the Network in Cutting Carbon for Geo-shifted Workloads
Yibo Guo, Amanda Tomlinson, Runlong Su +1
Organizations are increasingly offloading their workloads to cloud platforms. For workloads with relaxed deadlines, this presents an opportunity to reduce the total carbon footprin…
cs.CV2025
Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
Hangliang Ding, Dacheng Li, Runlong Su +4
Despite the promise of synthesizing high-fidelity videos, Diffusion Transformers (DiTs) with 3D full attention suffer from expensive inference due to the complexity of attention co…