Björn Ommer
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16Envisioning the Future, One Step at a Time
arXiv 2026
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
arXiv 2026
What If : Understanding Motion Through Sparse Interactions
arXiv 2025
TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training
ICCV 2025
DepthFM: Fast Monocular Depth Estimation with Flow Matching
arXiv 2024
ZigMa: A DiT-style Zigzag Mamba Diffusion Model
arXiv 2024
CleanDIFT: Diffusion Features without Noise
CVPR 2025 1
Does VLM Classification Benefit from LLM Description Semantics?
arXiv 2024
Scaling Image Tokenizers with Grouped Spherical Quantization
arXiv 2024
[MASK] is All You Need
arXiv 2024
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
CVPR 2025 1
Diffusion Models and Representation Learning: A Survey
arXiv 2024
Boosting Latent Diffusion with Flow Matching
arXiv 2023
Semi-Parametric Neural Image Synthesis
arXiv 2022
Taming Transformers for High-Resolution Image Synthesis
CVPR 2021 1
Learning Multi-Scale Photo Exposure Correction
CVPR 2021 1
Affiliations
Frequent co-authors
10from 16 papers