Publications
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
arXiv
•
•
Chandratreya, Charatan
VERA: Turning Video Models into Generalist Robot Policies
arXiv
•
•
Li, Kim, Bai
Large Video Planner
CoRL
•
•
Chen
Generative View Stitching
ICLR
•
•
Song
True Self-Supervised Novel View Synthesis is Transferable
ICLR
•
•
Mitchel, Ryu • ✨Oral
Locality in Image Diffusion Models Emerges from Data Statistics
NeurIPS
•
•
Lukoianov • ✨Spotlight
Date
TitleSubtitle
First Authors Venue 
Meshtryoshka Differentiable Rendering of Real-World Scenes via Mesh Rasterization
arXiv
MilliVid Hierarchical Latents for Long-Range Consistency in Video Generation
arXiv
VERA Turning Video Models into Generalist Robot Policies
arXiv
Scaling View Synthesis Transformers
CVPR
Large Video Planner
CoRL
Generative View Stitching
ICLR
True Self-Supervised Novel View Synthesis is Transferable
✨ ICLR
Selective Underfitting in Diffusion Models
arXiv
Locality in Image Diffusion Models Emerges from Data Statistics
✨ NeurIPS
Meschers Geometry Processing of Impossible Objects
SIGGRAPH
Controlling diverse robots by inferring Jacobian fields with deep networks
✨ Nature
History-Guided Video Diffusion
ICML
Diffusion Forcing Next-token Prediction Meets Full-Sequence Diffusion
NeurIPS
Neural Isometries Taming Transformations for Equivariant ML
NeurIPS
Score Distillation via Reparametrized DDIM
NeurIPS
FlowMap High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent
3DV
pixelSplat 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
✨ CVPR
Variational Barycentric Coordinates
✨ SIGGRAPH Asia
Diffusion with Forward Models Solving Stochastic Inverse Problems Without Direct Supervision
✨ NeurIPS
FlowCam Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
NeurIPS
Learning to render novel views from wide-baseline stereo pairs
CVPR
Neural Groundplans Persistent Neural Scene Representations from a Single Image
ICLR
Decomposing NeRF for Editing via Feature Field Distillation
NeurIPS
Unsupervised Discovery and Composition of Object Light Fields
TMLR
Neural Descriptor Fields SE(3)-Equivariant Object Representations for Manipulation
ICRA
Neural Fields in Visual Computing and Beyond
Eurographics STAR
Learning Signal-Agnostic Manifolds of Neural Fields
NeurIPS
3D Neural Scene Representations for Visuomotor Control
✨ CoRL
Deep Medial Fields
arXiv
Light Field Networks Neural Scene Representations with Single-Evaluation Rendering
✨ NeurIPS
MetaSDF Meta-learning Signed Distance Functions
NeurIPS
Implicit Neural Representations with Periodic Activation Functions
✨ NeurIPS
Scene Representation Networks Continuous 3D-Structure-Aware Neural Scene Representations
✨ NeurIPS
DeepVoxels Learning Persistent 3D Feature Embeddings
✨ CVPRMeshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization
arXiv
•
•
Charatan, Xu
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
arXiv
•
•
Chandratreya, Charatan
VERA: Turning Video Models into Generalist Robot Policies
arXiv
•
•
Li, Kim, Bai
Scaling View Synthesis Transformers
CVPR
•
•
Kim, Ryu
Large Video Planner
CoRL
•
•
Chen
Generative View Stitching
ICLR
•
•
Song
True Self-Supervised Novel View Synthesis is Transferable
ICLR
•
•
Mitchel, Ryu • ✨Oral
Selective Underfitting in Diffusion Models
arXiv
•
•
Song
Locality in Image Diffusion Models Emerges from Data Statistics
NeurIPS
•
•
Lukoianov • ✨Spotlight
Meschers: Geometry Processing of Impossible Objects
SIGGRAPH
•
•
Dodik
Controlling diverse robots by inferring Jacobian fields with deep networks
Nature
•
•
Li • ✨Nature Journal Article
History-Guided Video Diffusion
ICML
•
•
Song, Chen
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
NeurIPS
•
•
Chen
Neural Isometries: Taming Transformations for Equivariant ML
NeurIPS
•
•
Mitchel
Score Distillation via Reparametrized DDIM
NeurIPS
•
•
Lukoianov
FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent
3DV
•
•
Smith, Charatan
pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction
CVPR
•
•
Charatan • ✨Best Paper Runner-Up
Variational Barycentric Coordinates
SIGGRAPH Asia
•
•
Dodik • ✨Journal Track
Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
NeurIPS
•
•
Tewari, Yin • ✨Spotlight
FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow
NeurIPS
•
•
Smith
Learning to render novel views from wide-baseline stereo pairs
CVPR
•
•
Du
Neural Groundplans: Persistent Neural Scene Representations from a Single Image
ICLR
•
•
Sharma
Decomposing NeRF for Editing via Feature Field Distillation
NeurIPS
•
•
Kobayashi
Unsupervised Discovery and Composition of Object Light Fields
TMLR
•
•
Smith
Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation
ICRA
•
•
Simeonov, Du
Neural Fields in Visual Computing and Beyond
Eurographics STAR
•
•
Xie
Learning Signal-Agnostic Manifolds of Neural Fields
NeurIPS
•
•
Du
3D Neural Scene Representations for Visuomotor Control
CoRL
•
•
Li, Li • ✨Oral
Deep Medial Fields
arXiv
•
•
Rebain
Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering
NeurIPS
•
•
Sitzmann, Rezchikov • ✨Spotlight
MetaSDF: Meta-learning Signed Distance Functions
NeurIPS
•
•
Sitzmann
Implicit Neural Representations with Periodic Activation Functions
NeurIPS
•
•
Sitzmann, Martel • ✨Oral
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
NeurIPS
•
•
Sitzmann • ✨Outstanding New Directions - Honorable Mention
DeepVoxels: Learning Persistent 3D Feature Embeddings
CVPR
•
•
Sitzmann • ✨Oral