Publications

July 2025 International Conference on Machine Learning (ICML)

Adaptive Flow Matching for Resolving Small-Scale Physics

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Best paper award candidate, Oral

Zero-Shot Monocular Scene Flow Estimation in the Wild

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

arXiv Website
June 2025 Robotics: Science and Systems (RSS)

Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

Scaling Vision Pre-Training to 4K Resolution

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Recreating 1940s Tom and Jerry with Test-Time Training

June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Parallel Sequence Modeling via Generalization Spatial Propagation Network (GSPN)

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counter Factual Reasoning

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

NVILA: Efficient Frontier Visual Language Models

arXiv
June 2025 Robotics: Science and Systems (RSS)

NaVILA: Legged Robot Vision-Language-Action Model for Navigation

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Best paper award candidate, Oral

FoundationStereo: Zero-Shot Stereo Matching

arXiv
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations

arXiv Website
June 2025 Robotics: Science and Systems (RSS)

ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills

arXiv Website
June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

June 2025 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

3D-MVP: 3D Multiview Pretraining for Robotic Manipulation

arXiv
May 2025 International Conference on Robotics and Automation (ICRA)

SPOT: SE(3) Pose Trajectory Diffusion for Object-Centric Manipulation

arXiv
May 2025 International Conference on Robotics and Automation (ICRA)

Inference-Time Policy Steering with Human Interactions

arXiv
May 2025 International Conference on Robotics and Automation (ICRA)

Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning

arXiv
April 2025 International Conference on Learning Representations (ICLR)

VILA-U: Efficient and Unified Visual Language Understanding and Generation

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Truncated Consistency Models

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Think while You Generate: Discrete Diffusion with Planned Denoising

arXiv
April 2025 International Conference on Learning Representations (ICLR)

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Repulsive Latent Score Distillation Sampling for Diverse Sampling of Diffusion Models

arXiv pdf
April 2025 International Conference on Learning Representations (ICLR)
Oral

Proteina: Scaling Flow-based Protein Structure Generative Models

arXiv Website
April 2025 International Conference on Learning Representations (ICLR)
Oral

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

arXiv Website
April 2025 International Conference on Learning Representations (ICLR)

Not-So-Optimal Transport Flows for 3D Point Cloud Generation

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Neural Eulerian Scene Flow Fields

arXiv Website
April 2025 International Conference on Learning Representations (ICLR)

LongVILA: Scaling Long-Context Visual Language Models for Long Videos

arXiv
April 2025 International Conference on Learning Representations (ICLR)

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

pdf
April 2025 International Conference on Learning Representations (ICLR)

LlamaFlex: Many-in-One LLMs via Generalized Pruning and Weight Sharing

pdf
April 2025 International Conference on Learning Representations (ICLR)

InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Hymba: A Hybrid-head Architecture for Small Language Models

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Heavy-Tailed Diffusion Models

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Gated Delta Networks: Improving Mamba2 with Delta Rule

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Energy-based Diffusion Language Models for Text Generation

arXiv
April 2025 International Conference on Learning Representations (ICLR)

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

arXiv
March 2025 International Conference on 3D Vision (3DV)

Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces

arXiv
March 2025 ArXiv Preprint

GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

arXiv
February 2025 Nature Communications Earth & Environment

Residual corrective diffusion modeling for km-scale atmospheric downscaling

arXiv Website
February 2025 IEEE Winter Conference on Applications of Computer Vision (WACV)

HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors

arXiv
January 2025 Transactions on Machine Learning Research

Directed Graph Generation with Heat Kernels

pdf
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

Molecule Generation with Fragment Retrieval Augmentation

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)
Spotlight

Memorize What Matters: Emergent Scene Decomposition from Multitraverse

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

L4GM: Large 4D Gaussian Reconstruction Model

arXiv
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

FACTORSIM: Generative Simulation via Factorized Representation

arXiv
December 2024 ACM Transactions on Graphics (SIGGRAPH ASIA)

DiffUHaul: A Training-Free Method for Object Dragging in Images

arXiv Website
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

Cosine Autoencoder with Extremely Narrow Bottleneck for Image Restoration

Website pdf
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

CosAE: Learnable Fourier Series for Image Restoration

pdf
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

Compact Language Models via Pruning and Knowledge Distillation

arXiv
December 2024 ACM Transactions on Graphics (SIGGRAPH ASIA)

BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs

pdf
December 2024 Advances in Neural Information Processing Systems (NeurIPS)

Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization

arXiv
November 2024 Conference on Robot Learning (CoRL)

SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment

arXiv Website
November 2024 Conference on Robot Learning (CoRL)

RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics

arXiv
November 2024 Conference on Robot Learning (CoRL)

Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions

arXiv Website
November 2024 Conference on Robot Learning (CoRL)

DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning

arXiv
November 2024 Conference on Robot Learning (CoRL)

Avoid Everything: Model-Free Collision Avoidance with Expert-Guided Fine-Tuning

pdf
October 2024 Transactions on Machine Learning Research

Universal Functional Regression with Neural Operator Flows

arXiv code
October 2024 International Conference on Intelligent Robots and Systems (IROS)

SSCBench: Monocular 3D Semantic Scene Completion Benchmark in Street Views

arXiv Website
October 2024 Workshop on the Algorithmic Foundations of Robotics (WAFR)

DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation

arXiv Website
October 2024 Transactions on Machine Learning Research

AGG: Amortized Generative 3D Gaussians for Single Image to 3D

arXiv Website
September 2024 European Conference on Computer Vision (ECCV)

MEVG: Multi-event Video Generation with Text-to-Video Models

arXiv
September 2024 European Conference on Computer Vision (ECCV)

LITA: Language Instructed Temporal-localization Assistant

arXiv
September 2024 Transactions on Machine Learning Research

Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs

arXiv
September 2024 npj Robotics

FALCON: Fourier Adaptive Learning and Control for Disturbance Rejection Under Extreme Turbulence

pdf
September 2024 European Conference on Computer Vision (ECCV)

DiffiT: Diffusion Vision Transformers for Image Generation

arXiv Website
September 2024 Geophysical Journal International

Deep Neural Helmholtz Operators for 3D Elastic Wave Propagation and Inversion

arXiv
September 2024 European Conference on Computer Vision (ECCV)

COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation

arXiv Website
September 2024 European Conference on Computer Vision (ECCV)

Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos

arXiv pdf
September 2024 European Conference on Computer Vision (ECCV)

A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties

arXiv
August 2024 Transactions on Machine Learning Research

Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs

pdf
August 2024 Computational Visual Media

LISA: Localized Image Stylization with Audio via Implicit Neural Representation

arXiv
August 2024 ACM SIGGRAPH / Eurographics Symposium on Computer Animation

Learning to Move Like Professional Counter-Strike Players Learning to Move Like Professional Counter-Strike Players

arXiv Website
August 2024 Transactions on Machine Learning Research

Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction

pdf
July 2024 Transactions on Machine Learning Research

Sparse Contextual CDF Regression

pdf
July 2024 Robotics: Science and Systems (RSS)

RVT-2: Learning Precise Manipulation from Few Demonstrations

arXiv
July 2024 Neural Networks

Robust Sound-Guided Image Manipulation

arXiv
July 2024 International Conference on Machine Learning (ICML)

Neural Operators with Localized Integral and Differential Kernels

arXiv
July 2024 International Conference on Machine Learning (ICML)
Oral

Flextron: Many-in-One Flexible Large Language Model

arXiv
July 2024 International Conference on Machine Learning (ICML)

FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models

arXiv
July 2024 International Conference on Machine Learning (ICML)

Equivariant Graph Neural Operator for Modeling 3D Dynamics

arXiv
July 2024 International Conference on Machine Learning (ICML)

DoRA: Weight-decomposed Low-rank Adaptation

arXiv
July 2024 International Conference on Machine Learning (ICML)

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents

Website pdf code
July 2024 International Conference on Machine Learning (ICML)

Compositional Text-to-Image Generation with Dense Blob Representations

arXiv Website
July 2024 Robotics: Science and Systems (RSS)

AutoMate: Specialist and Generalist Assembly Policies over Diverse Geometries

Website pdf
July 2024 International Conference on Machine Learning (ICML)

Align Your Steps: Optimizing Sampling Schedules in Diffusion Models

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

VILA: On pretraining for vision language models

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

RegionGPT: Towards Region Understanding Vision Language Model

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows

pdf
June 2024 CVPR Workshop on Human Motion Generation (HuMoGen)

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Improving Distant 3D Object Detection Using 2D Box Supervision

arXiv
June 2024 ArXiv Preprint

Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation

arXiv
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Dream-in-4D: A Unified Approach for Text- and Image-guided 4D Scene Generation

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

COLMAP-Free 3D Gaussian Splatting

arXiv Website
June 2024 ArXiv Preprint

An Empirical Study of Mamba-based Language Models

arXiv Website
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

AM-RADIO: Agglomerative Model - Reduce All Domains Into One

arXiv Website pdf
June 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

arXiv Website
May 2024 International Conference on Learning Representations (ICLR)

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space

arXiv
May 2024 International Conference on Artificial Intelligence and Statistics (AISTATS)

Timing as an Action: Learning When to Observe and Act

pdf
May 2024 International Conference on Learning Representations (ICLR)

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

pdf
May 2024 International Conference on Learning Representations (ICLR)

Learning to Jointly Understand Visual and Tactile Signals

pdf
May 2024 International Conference on Learning Representations (ICLR)

Guaranteed Approximation Bounds for Mixed-Precision Neural Operators

pdf
May 2024 International Conference on Learning Representations (ICLR)

FasterViT: Fast Vision Transformers with Hierarchical Attention

arXiv Website
May 2024 International Conference on Learning Representations (ICLR)

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

arXiv Website
May 2024 ICLR Workshop on Climate Change AI

AI-driven emulation of ocean dynamics on sub-seasonal scales

May 2024 International Conference on Learning Representations (ICLR)

A Variational Perspective on Solving Inverse Problems with Diffusion Models

arXiv
May 2024 International Conference on Learning Representations (ICLR)

3D Reconstruction with Generalizable Neural Fields using Scene Priors

arXiv Website
April 2024 Nature Reviews Physics

Neural operators for accelerating scientific simulations and design

pdf
March 2024 International Conference on 3D Vision (3DV)
Spotlight

Partial-View Object View Synthesis via Filtering Inversion

arXiv Website
March 2024 International Conference on 3D Vision (3DV)
Spotlight

PACE: Human and Camera Motion Estimation from in-the-wild Videos

arXiv
March 2024 Transactions on Machine Learning Research

Functional Linear Regression of Cumulative Distribution Functions

pdf
March 2024 International Conference on 3D Vision (3DV)
Oral

FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization

arXiv Website
March 2024 Bulletin of the Seismological Society of America

Broadband ground motion synthesis via generative adversarial neural operators: Development and validation

pdf
February 2024 Handbook of Numerical Analysis

Operator Learning: Algorithms and Analysis

arXiv
February 2024 International Workshop on Mobile Computing Systems and Applications

Mobile AR Depth Estimation: Challenges \& Prospects

arXiv
January 2024 Frontiers in Marine Science

Promoting best practices in ocean forecasting through an Operational Readiness Level

pdf
January 2024 SIAM Journal on Numerical Analysis

Learning Homogenization For Elliptic Operators

arXiv
December 2023 Symbiosis of Deep Learning and Differential Equations III, Neural Information Processing Systems (NeurIPS)

Physics-informed neural operators with exact differentiation on arbitrary geometries

pdf
December 2023 Geophysical Research Letters

Phase Neural Operator for Multi-Station Picking of Seismic Arrivals

pdf code project
December 2023 Advances in Neural Information Processing Systems (NeurIPS)

Geometry-informed neural operator for large-scale 3D PDEs

pdf
December 2023 Advances in Neural Information Processing Systems (NeurIPS)

Generalizable One-shot Neural Head Avatar

arXiv
December 2023 Advances in Neural Information Processing Systems (NeurIPS)

Convolutional State Space Models for Long-Range Spatiotemporal Modeling

arXiv pdf
November 2023 Conference on Robot Learning (CoRL)

MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations

arXiv Website
October 2023 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Vicinity Vision Transformer

pdf
October 2023 IEEE International Conference on Computer Vision (ICCV)

The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion

arXiv
October 2023 IEEE International Conference on Computer Vision (ICCV)

TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models

arXiv Website
October 2023 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models

arXiv
October 2023 IEEE International Conference on Computer Vision (ICCV)

RANA: Relightable and Articulated Neural Avatars

arXiv Website
October 2023 IEEE International Conference on Computer Vision (ICCV)
Oral

PhysDiff: Physics-Guided Human Motion Diffusion Model

arXiv Website
October 2023 IEEE International Conference on Computer Vision (ICCV)

Learning Human Dynamics in Autonomous Driving Scenarios

pdf
October 2023 International Conference on Intelligent Robots and Systems (IROS)

HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions

arXiv Website
October 2023 IEEE International Conference on Computer Vision (ICCV)
Oral

Generative Novel View Synthesis with 3D-Aware Diffusion Models

arXiv Website
October 2023 IEEE International Conference on Computer Vision (ICCV)

Fully Attentional Networks with Self-emerging Token Labeling

arXiv pdf
October 2023 IEEE International Conference on Computer Vision (ICCV)

FocalFormer3D: Focusing on Hard Instance for 3D Object Detection

arXiv Website
October 2023 IEEE International Conference on Computer Vision (ICCV)

FB-BEV: BEV Representation from Forward-Backward View Transformations

arXiv Website
October 2023 IEEE International Conference on Computer Vision (ICCV)

End-to-end 3D Tracking with Decoupled Queries

arXiv Website pdf
October 2023 IEEE International Conference on Computer Vision (ICCV)

DreamTeacher: Pretraining Image Backbones with Deep Generative Models

arXiv Website
October 2023 Transactions on Machine Learning Research

Differentially Private Diffusion Models

arXiv pdf
August 2023 ACM Transactions on Graphics (SIGGRAPH)

Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization

arXiv Website
August 2023 ACM Transactions on Graphics (SIGGRAPH)

Real-Time Radiance Fields for Single-Image Portrait View Synthesis

arXiv Website
August 2023 ACM Transactions on Graphics (SIGGRAPH)
Best paper honorable mention

Learning Physically Simulated Tennis Players from Broadcast Videos

arXiv
July 2023 International Conference on Machine Learning (ICML)

Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation

pdf
July 2023 International Conference on Machine Learning (ICML)

I^2SB: Image-to-Image Schrödinger Bridge

arXiv Website
July 2023 International Conference on Machine Learning (ICML)

Global Context Vision Transformers

arXiv Website
July 2023 International Conference on Machine Learning (ICML)

Fast Sampling of Diffusion Models via Operator Learning

arXiv
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Zero-shot Pose Transfer for Unrigged Stylized 3D Characters

pdf
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

VoxFormer: Sparse voxel transformer for camera-based 3D semantic scene completion

arXiv code
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Vision Transformers Are Good Mask Auto-Labelers

arXiv code
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

arXiv
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

arXiv Website
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

The Best Defense is a Good Offense: Adversarial Augmentation Against Adversarial Attacks

arXiv Website
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Models

arXiv
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models

arXiv
June 2023 CVPR Workshop on Advances in NeRF for the Metaverse (XRNeRF)

One-Shot Neural Fields for 3D Object Understanding

arXiv
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models

arXiv Website
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Magic3D: High-Resolution Text-to-3D Content Creation

arXiv Website
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Highlight

Heterogeneous Continual Learning

pdf
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Global Vision Transformer Pruning with Hessian-Aware Saliency

arXiv
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

GazeNeRF: 3D-Aware Gaze Redirection with Neural Radiance Fields

arXiv
June 2023 CVPR Workshop on End-to-end Autonomous Driving

FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation

arXiv Website
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids

arXiv
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

arXiv Website video
June 2023 IEEE Intelligent Vehicles Symposium

Augmenting Legacy Networks for Flexible Inference

pdf
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

arXiv Website
June 2023 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Affordance Diffusion: Synthesizing Hand-Object Interactions

arXiv Website video
May 2023 International Conference on Robotics and Automation (ICRA)

RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control

arXiv Website video
May 2023 International Conference on Learning Representations (ICLR)

Pseudoinverse-Guided Diffusion Models for Inverse Problems

May 2023 International Conference on Robotics and Automation (ICRA)

PROGPROMPT: Generating Situated Robot Task Plans using Large Language Models

arXiv Website
May 2023 International Conference on Robotics and Automation (ICRA)

Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation

arXiv Website video
May 2023 International Conference on Robotics and Automation (ICRA)

Online Consistent Video Depth using Continuous Geometric Representations

pdf
May 2023 International Conference on Learning Representations (ICLR)

GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

arXiv
May 2023 International Conference on Learning Representations (ICLR)

Dual Diffusion Implicit Bridges for Image-to-Image Translation

arXiv
March 2023 ArXiv Preprint

Prismer: A Vision-Language Model with An Ensemble of Experts

arXiv Website code demo
February 2023 ArXiv Preprint

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

arXiv
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

Test-time prompt tuning for zero-shot generalization in vision-language models

arXiv website code
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

Structural Pruning via Latency-Saliency Knapsack

arXiv Website
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

MinVIS: A minimal video instance segmentation framework without video-based training

arXiv code
December 2022 Conference on Robot Learning (CoRL)

MegaPose: 6D Pose Estimation of Novel Objects via Render and Compare

arXiv Website video openreview
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

LISA: Learning Interpretable Skill Abstractions from Language

arXiv
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

LION: Latent Point Diffusion Models for 3D Shape Generation

arXiv Website
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

GENIE: Higher-Order Denoising Diffusion Solvers

arXiv Website
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

Embodied Scene-aware Human Pose Estimation

arXiv Website video
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

Denoising Diffusion Restoration Models

arXiv Website code
December 2022 Advances in Neural Information Processing Systems (NeurIPS)

Concrete Score Matching: Generalized Score Matching for Discrete Data

arXiv
November 2022 Medical Image Analysis

Towards Annotation-efficient Segmentation via Image-to-image Translation

arXiv
October 2022 European Conference on Computer Vision (ECCV)

Sound-Guided Semantic Video Generation

arXiv
October 2022 European Conference on Computer Vision (ECCV)

Scraping Textures from Natural Images for Synthesis and Editing

Website pdf video
October 2022 ECCV Workshop on Learning to Generate 3D Shapes and Scenes

RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis

arXiv Website video
October 2022 British Machine Vision Conference (BMVC)

Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks

arXiv
October 2022 European Conference on Computer Vision (ECCV)

Neural Light Field Estimation for Outdoor Scenes with Differentiable Virtual Object Insertion

arXiv
October 2022 European Conference on Computer Vision (ECCV)

Multimodal Conditional Image Synthesis with Product-of-Experts GANs

arXiv Website
October 2022 European Conference on Computer Vision (ECCV)

LANA: Latency Aware Network Acceleration

arXiv
October 2022 European Conference on Computer Vision (ECCV)

Autoregressive 3D shape generation via canonical mapping

arXiv
October 2022 European Conference on Computer Vision (ECCV)

Audio-Visual Segmentation

arXiv code website
October 2022 International Conference on Intelligent Robots and Systems (IROS)

6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark

arXiv website
September 2022 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Partial Convolution for Padding, Inpainting, and Image Synthesis

pdf
July 2022 International Conference on Machine Learning (ICML)

Understanding The Robustness in Vision Transformers

arXiv code
July 2022 International Conference on Machine Learning (ICML)

Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework

arXiv
July 2022 International Conference on Machine Learning (ICML)

Diffusion Models for Adversarial Purification

arXiv Website
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

When to Prune? A Policy towards Early Structural Pruning

arXiv
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects

arXiv Website
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Sound-Guided Semantic Image Manipulation

arXiv Website
June 2022 International Conference on Computational Science (ICCS)

Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations

arXiv
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Panoptic SegFormer: Delving deeper into panoptic segmentation with transformers

arXiv code
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

GroupViT: Semantic Segmentation Emerges From Text Supervision

video
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

GradViT: Gradient Inversion of Vision Transformers

arXiv Website
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Oral

GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras

arXiv Website
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

FreeSOLO: Learning to Segment Objects without Annotations

arXiv code
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Efficient Geometry-aware 3D Generative Adversarial Networks

arXiv Website
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs

video
June 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

A-ViT: Adaptive Tokens for Efficient Vision Transformer

arXiv Website
May 2022 International Conference on Robotics and Automation (ICRA)

Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image

arXiv website
May 2022 International Conference on Robotics and Automation (ICRA)

PredictionNet: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulation

arXiv video
May 2022 International Conference on Robotics and Automation (ICRA)

Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation

arXiv website
May 2022 International Journal of Computer Vision (IJCV)

Displacement-Invariant Cost Computation for Efficient Stereo Matching

arXiv pdf
April 2022 International Conference on Learning Representations (ICLR)

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs

arXiv Website
April 2022 International Conference on Learning Representations (ICLR)

Score-Based Generative Modeling with Critically-Damped Langevin Diffusion

arXiv Website
April 2022 ArXiv Preprint

M$^2$BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation

arXiv website
March 2022 International Journal of Computer Vision (IJCV)

Learning contrastive representation for semantic correspondence

arXiv
March 2022 ArXiv Preprint

DRaCoN--Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars

arXiv Website
February 2022 AAAI Conference on Artificial Intelligence (AAAI)

Neural Interferometry: Image Reconstruction from Astronomical Interferometers using Transformer-Conditioned Neural Fields

pdf
February 2022 ArXiv Preprint

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

arXiv
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

SegFormer: Simple and efficient design for semantic segmentation with transformers

arXiv code video demo tutorial zhihu
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

Score-based Generative Modeling in Latent Space

arXiv Website
December 2021 International Conference on 3D Vision (3DV)

KAMA: 3D Keypoint Aware Body Mesh Articulation

arXiv video
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction

arXiv
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence

arXiv Website
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

Coupled Segmentation and Edge Learning via Dynamic Graph Propagation

pdf
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

Coupled Segmentation and Edge Learning Using Dynamic Graph Propagation

pdf
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

Controllable and Compositional Generation with Latent-Space Energy-Based Models

arXiv Website
December 2021 Advances in Neural Information Processing Systems (NeurIPS)

A Contrastive Learning Approach for Training Variational Autoencoder Priors

arXiv
November 2021 British Machine Vision Conference (BMVC)

Noise-Aware Video Saliency Prediction

arXiv video
November 2021 British Machine Vision Conference (BMVC)

Hierarchical Contrastive Motion Learning for Video Action Recognition

arXiv
October 2021 IEEE International Conference on Computer Vision (ICCV)

Self-Supervised Real-to-Sim Scene Generation

arXiv project
October 2021 IEEE International Conference on Computer Vision (ICCV)

Self-Supervised Object Detection via Generative Image Synthesis

arXiv
October 2021 International Symposium on Software Reliability Engineering (ISSRE)

Optimizing Selective Protection for CNN Resilience

pdf
October 2021 ArXiv Preprint

NViT: Vision Transformer Compression and Parameter Redistribution

arXiv
October 2021 IEEE International Conference on Computer Vision (ICCV)
Oral

Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting

arXiv Website
October 2021 IEEE International Conference on Computer Vision (ICCV)
Oral

GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds

arXiv Website
September 2021 International Conference on Intelligent Robots and Systems (IROS)

Multi-View Fusion for Multi-Level Robotic Scene Understanding

arXiv video
September 2021 International Conference on Intelligent Robots and Systems (IROS)

Joint Space Control via Deep Reinforcement Learning

arXiv video
July 2021 IEEE Transactions on Automation Science and Engineering (TASE)

RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies

arXiv
July 2021 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation

pdf
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Oral

Weakly-Supervised Physically Unconstrained Gaze Estimation

arXiv
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View Generalization for Single Image Textured 3D Models

Website pdf video
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models

pdf
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

See through Gradients: Image Batch Recovery via GradInversion

arXiv
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Optimal Quantization Using Scaled Codebook

pdf
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Oral

One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

arXiv Website
June 2021 International Conference on Computational Science (ICCS)

NVIDIA SimNet: An AI-accelerated multi-physics simulation framework

arXiv pdf
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Learning to Track Instances without Video Annotations

June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Dual Contrastive Loss and Attention for GANs

pdf video
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

code video
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

arXiv project
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Deep Two-View Structure-from-Motion Revisited

arXiv code
June 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Oral, Best student paper honorable mention

Binary TTC: A Temporal Geofence for Autonomous Navigation

arXiv Website
June 2021 ArXiv Preprint

Adversarial Motion Modelling Helps Semi-Supervised Hand Pose Estimation

arXiv
May 2021 International Conference on Learning Representations (ICLR)

VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models

arXiv code
May 2021 International Conference on Learning Representations (ICLR)

Parameter Efficient Multimodal Transformers for Video Representation Learning

arXiv
May 2021 ICLR Workshop on Synthetic Data Generation

NViSII: A Scriptable Tool for Photorealistic Image Generation

arXiv code
May 2021 International Conference on Learning Representations (ICLR)

Learning continuous environment fields via implicit functions

arXiv
May 2021 International Conference on Robotics and Automation (ICRA)

Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs

arXiv project video
May 2021 International Conference on Robotics and Automation (ICRA)

Fast Uncertainty Quantification for Deep Object Pose Estimation

arXiv project video
March 2021 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games

Robust Vision-Based Cheat Detection in Competitive Gaming

arXiv
March 2021 ArXiv Preprint

Neural Trajectory Fields for Dynamic Novel View Synthesis

arXiv
March 2021 IEEE Intelligent Vehicles Symposium

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

arXiv
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

Online adaptation for consistent mesh reconstruction in the wild

video
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

On the Distance between Two Neural Networks and the Stability of Learning

arXiv code
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

NVAE: A Deep Hierarchical Variational Autoencoder

arXiv Website
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

Neural FFTs for Universal Texture Image Synthesis

pdf
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

Generative View Synthesis: From Single-view Semantics to Novel-view Images

arXiv Website code
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

Convolutional Tensor-Train LSTM for Spatio-temporal Learning

arXiv
December 2020 Advances in Neural Information Processing Systems (NeurIPS)

Accelerating reinforcement learning through GPU atari emulation

arXiv Website
October 2020 European Conference on Computer Vision (ECCV)

Self-supervised single-view 3D reconstruction via semantic consistency

video
October 2020 International Conference on Intelligent Robots and Systems (IROS)

MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views

arXiv video
October 2020 International Conference on Intelligent Robots and Systems (IROS)

Indirect Object-to-Robot Pose Estimation from an External Monocular RGB Camera

arXiv video
August 2020 European Conference on Computer Vision (ECCV)

World-Consistent Video-to-Video Synthesis

arXiv Website
August 2020 European Conference on Computer Vision (ECCV)

UFO2: A Unified Framework towards Omni-supervised Object Detection

arXiv
August 2020 European Conference on Computer Vision (ECCV)
Oral

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

arXiv
August 2020 European Conference on Computer Vision (ECCV)
Spotlight

Contrastive Learning for Weakly Supervised Phrase Grounding

arXiv Website
July 2020 International Conference on Machine Learning (ICML)

Undirected Graphical Models as Approximate Posteriors

arXiv
July 2020 ArXiv Preprint

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

arXiv pdf video
July 2020 International Conference on Machine Learning (ICML)

Angular Visual Hardness

arXiv
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild

arXiv
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

arXiv code
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Two-shot Spatially-varying BRDF and Shape Estimation

arXiv Website
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Semi-Supervised Semantic Image Segmentation with Self-correcting Networks

arXiv
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self-Supervised Viewpoint Learning from Image Collections

arXiv
June 2020 IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)

PyTorchFI: A Runtime Perturbation Tool for DNNs

Website
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera

arXiv Website
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Meshlet Priors for 3D Mesh Reconstruction

arXiv video
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Instance-aware, Context-focused, and Memory-efficient Weakly-Supervised Object Detection

arXiv
June 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Bi3D: Stereo Depth Estimation via Binary Classifications

arXiv Website
May 2020 International Conference on Robotics and Automation (ICRA)

Toward Sim-to-Real Directional Semantic Grasping

arXiv video
May 2020 International Conference on Robotics and Automation (ICRA)

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System

arXiv Website
May 2020 International Conference on Robotics and Automation (ICRA)

Camera-to-robot pose estimation from a single image

arXiv website video
March 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)

NRMVS: Non-Rigid Multi-View Stereo

pdf