activity
20242026
collaborators

6 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.LG2024

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…