8 papers
Telescopic Language Models
Zhilin Guo, Boqiao Zhang, Hakan Aktas +14
One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Langu…
Matryoshka Gaussian Splatting
Zhilin Guo, Boqiao Zhang, Hakan Aktas +11
The ability to render scenes at adjustable fidelity from a single model, known as level of detail (LoD), is crucial for practical deployment of 3D Gaussian Splatting (3DGS). Existi…
PoseCraft: Tokenized 3D Body Landmark and Camera Conditioning for Photorealistic Human Image Synthesis
Zhilin Guo, Jing Yang, Kyle Fogarty +9
Digitizing humans and synthesizing photorealistic avatars with explicit 3D pose and camera controls are central to VR, telepresence, and entertainment. Existing skinning-based work…
Restereo: Diffusion stereo video generation and restoration
Xingchang Huang, Ashish Kumar Singh, Florian Dubost +6
Stereo video generation has been gaining increasing attention with recent advancements in video diffusion models. However, most existing methods focus on generating 3D stereoscopic…
Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts
Ibtihel Amara, Ahmed Imtiaz Humayun, Ivana Kajic +12
Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstra…
Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models
Cristina N. Vasconcelos, Abdullah Rashwan, Austin Waters +22
We address the long-standing problem of how to learn effective pixel-based image diffusion models at scale, introducing a remarkably simple greedy growing method for stable trainin…
Planted: a dataset for planted forest identification from multi-satellite time series
Luis Miguel Pazos-Outón, Cristina Nader Vasconcelos, Anton Raichuk +3
Protecting and restoring forest ecosystems is critical for biodiversity conservation and carbon sequestration. Forest monitoring on a global scale is essential for prioritizing and…
Blue noise for diffusion models
Xingchang Huang, Corentin Salaün, Cristina Vasconcelos +3
Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed b…