Search Results for author:
Found 9 papers, 2 papers with code
Variational Rectified Flow Matching
We study Variational Rectified Flow Matching, a framework that enhances classic rectified flow matching by modeling multi-modal velocity vector-fields.
On Inductive Biases That Enable Generalization of Diffusion Transformers
Furthermore, we empirically find that both the placement and the effective attention size of these local attention windows are crucial factors.
StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D
Our analysis identifies the core of these challenges as the interaction among noise levels in the 2D diffusion process, the architecture of the diffusion network, and the 3D model representation.
CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstruction
Recent advances in neural reconstruction using posed image sequences have made remarkable progress.
GAUDI: A Neural Architect for Immersive 3D Scene Generation
We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera.
Ranked #1 on
Image Generation
on ARKitScenes
Fast and Explicit Neural View Synthesis
We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects.
MetricOpt: Learning to Optimize Black-Box Evaluation Metrics
This leads to consistent improvements since the value function provides effective metric supervision during finetuning, and helps to correct the potential bias of loss-only supervision.
Learning to Branch for Multi-Task Learning
Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of a network.
Adaptive Variance for Changing Sparse-Reward Environments
Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration.
