Yanchao Yang

25

Papers

3

Total Citations

Papers (25)

MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery

$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding

InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

Coarse-To-Fine Region Selection and Matching

S2F: Slow-To-Fast Interpolator Flow

Unsupervised Moving Object Detection via Contextual Information Separation

Dense Depth Posterior (DDP) From Single Image and Sparse Range

FDA: Fourier Domain Adaptation for Semantic Segmentation

Learning to Manipulate Individual Objects in an Image

Phase Consistent Ecological Domain Adaptation

DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping

Learning Semantic-Aware Dynamics for Video Prediction

Domain Adaptation on Point Clouds via Geometry-Aware Implicits

ADeLA: Automatic Dense Labeling With Attention for Viewpoint Shift in Semantic Segmentation

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

JacobiNeRF: NeRF Shaping With Mutual Information Gradients

Self-Occlusions and Disocclusions in Causal Video Object Segmentation

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

Structure-Aware Surface Reconstruction via Primitive Assembly

GIMO: Gaze-Informed Human Motion Prediction in Context

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

SpOT: Spatiotemporal Modeling for 3D Object Tracking

HuMoCon: Concept Discovery for Human Motion Understanding