6 papers
Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
Minseok Joo, Dogyun Park, Taehoon Lee +2
Maintaining long-term geometric consistency remains challenging for long-horizon autoregressive video generation. Memory-augmented generative models address this by retrieving hist…
EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow
Dogyun Park, Yanyu Li, Sergey Tulyakov +1
Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling st…
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
Moayed Haji-Ali, Willi Menapace, Ivan Skorokhodov +6
Diffusion transformers (DiTs) achieve high generative quality but lock FLOPs to image resolution, limiting principled latency-quality trade-offs, and allocate computation uniformly…
Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
Dogyun Park, Moayed Haji-Ali, Yanyu Li +5
Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively exp…
Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
Dogyun Park, Taehoon Lee, Minseok Joo +1
Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the…
Constant Acceleration Flow
Dogyun Park, Sojin Lee, Sihyeon Kim +3
Rectified flow and reflow procedures have significantly advanced fast generation by progressively straightening ordinary differential equation (ODE) flows. They operate under the a…