Jiaqi Yang

Affiliations

Institute for Interdisciplinary Information Sciences, Tsinghua University

papers

551

total citations

papers (24)

3D Registration With Maximal Cliques

CVPR 2023arXiv

166

citations

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

ICCV 2025arXiv

citations

Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP

NEURIPS 2021arXiv

citations

iQuery: Instruments As Queries for Audio-Visual Sound Separation

CVPR 2023arXiv

citations

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

NEURIPS 2021arXiv

citations

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

ICLR 2025

citations

MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices

CVPR 2025arXiv

citations

Hierarchical Prior Mining for Non-local Multi-View Stereo

ICCV 2023arXiv

citations

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

NEURIPS 2022arXiv

citations

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

NEURIPS 2021arXiv

citations

Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

ECCV 2022arXiv

citations

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation

CVPR 2025arXiv

citations

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

ICCV 2023arXiv

citations

DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data

AAAI 2025arXiv

citations

SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network

AAAI 2025arXiv

citations

Unlocking Generalization Power in LiDAR Point Cloud Registration

CVPR 2025arXiv

citations

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

ICCV 2025arXiv

citations

BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation

ICCV 2025arXiv

citations

PhyIR: Physics-Based Inverse Rendering for Panoramic Indoor Images

CVPR 2022

citations

ArgMatch: Adaptive Refinement Gathering for Efficient Dense Matching

ICCV 2025

citations

MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP

ICCV 2025arXiv

citations

Jiaqi Yang

Affiliations

papers (24)

3D Registration With Maximal Cliques

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP

iQuery: Instruments As Queries for Audio-Visual Sound Separation

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

Multi-View Inverse Rendering for Large-Scale Real-World Indoor Scenes

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices

Hierarchical Prior Mining for Non-local Multi-View Stereo

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data

SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network

Unlocking Generalization Power in LiDAR Point Cloud Registration

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation

PhyIR: Physics-Based Inverse Rendering for Panoramic Indoor Images

ArgMatch: Adaptive Refinement Gathering for Efficient Dense Matching

MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP

papers (24)

3D Registration With Maximal Cliques

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP

iQuery: Instruments As Queries for Audio-Visual Sound Separation

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation

Multi-View Inverse Rendering for Large-Scale Real-World Indoor Scenes

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices

Hierarchical Prior Mining for Non-local Multi-View Stereo

Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data

SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network

Unlocking Generalization Power in LiDAR Point Cloud Registration

HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration

BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation

PhyIR: Physics-Based Inverse Rendering for Panoramic Indoor Images

ArgMatch: Adaptive Refinement Gathering for Efficient Dense Matching

MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP