Albert Pumarola

Engineering · Physical Sciences

17h-index3.8kcitations64works1.32yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

3D Shape Modeling and Analysis(26), Computer Graphics and Visualization Techniques(22), Advanced Vision and Imaging(15), Generative Adversarial Networks and Image Synthesis(15), Human Pose and Action Recognition(14)

Publications64 total

SneakPeek: Future-Guided Instructional Streaming Video Generation
arXiv (Cornell University)·2025Open Access
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
2025
Autoregressive Distillation of Diffusion Transformers
2025
Autoregressive Distillation of Diffusion Transformers
arXiv (Cornell University)·2025Open Access
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 2 citedOpen Access
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
arXiv (Cornell University)·2025Open Access
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
arXiv (Cornell University)·2025Open Access
Movie Gen: A Cast of Media Foundation Models
arXiv (Cornell University)·2024· 7 citedOpen Access
Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation
arXiv (Cornell University)·2024Open Access
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Animated Stickers: Bringing Stickers to Life with Video Diffusion
arXiv (Cornell University)·2024· 1 citedOpen Access
StyleAvatar: Stylizing Animatable Head Avatars
2024· 4 cited
fMPI: Fast Novel View Synthesis in the Wild with Layered Scene Representations
arXiv (Cornell University)·2023Open Access
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
arXiv (Cornell University)·2023· 1 citedOpen Access
Bespoke Solvers for Generative Flow Models
arXiv (Cornell University)·2023· 2 citedOpen Access
BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
2023· 16 cited
Re-ReND: Real-time Rendering of NeRFs across Devices
2023· 17 cited
Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
2023· 83 cited
BoDiffusion: Diffusing Sparse Observations for Full-Body Human Motion Synthesis
arXiv (Cornell University)·2023· 1 citedOpen Access
Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
arXiv (Cornell University)·2023· 2 citedOpen Access
page 1 of 4Next →

Frequent Co-authors

Francesc Moreno-Noguer(26), Ali Thabet(16), Alberto Sanfeliu(15), Artsiom Sanakoyeu(11), Antonio Agudo(9), Enric Corona(8), Jonas Köhler(6), Guillem Alenyà(5), Yuming Du(5), Pablo Arbeláez(5), Gerard Pons‐Moll(4), Bernard Ghanem(4), Angela Castillo(4), Peizhao Zhang(4), P. Vajda(4), Edgar Schönfeld(4), Juan C. Pérez(4), Aleix M. Martı́nez(3), Yaron Lipman(3), Markos Georgopoulos(3)