Zhiyang Dou
20 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (42) π€ Dynamic Duo (10)
π
Renaissance Researcher
(5)
ποΈ
Keyword Collector
(87)
π
Trend Setter
π
Century Club Β· Bronze
β‘
Prolific Year Β· Prolific
Top co-authors
Research topics
Computer Vision
(11)
Deep Learning
(11)
Artificial Intelligence
(9)
Machine Learning
(8)
Core AI
(8)
Analysis
(7)
Architectures
(5)
Generation
(5)
Learning Types Β· Machine Learning
(5)
Models
(4)
Application Areas
(2)
Learning Paradigms
(2)
Learning Types Β· Deep Learning
(2)
Optimization & Theory
(2)
Knowledge & Reasoning
(1)
Keywords
motion generation
(2)
zero-shot learning
(2)
human-scene interaction
(2)
foundation model
(2)
transformer architecture
(2)
3d reconstruction
(2)
diffusion model
(2)
temporal consistency
(2)
reinforcement learning
(2)
geometry reconstruction
(2)
autoregressive generation
(1)
mathematical reasoning
(1)
open-vocabulary detection
(1)
monocular depth estimation
(1)
semantic segmentation
(1)
object detection
(1)
human motion
(1)
motion synthesis
(1)
error detection
(1)
neural network optimization
(1)
Papers
MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly
CVPR 2026
PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction
CVPR 2026
Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
CVPR 2025
Boosting Segment Anything Model Towards Open-Vocabulary Learning
AAAI 2025
CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs
ICLR 2025
DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image
ICLR 2025
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data
ICCV 2025
ModSkill: Physical Character Skill Modularization
ICCV 2025
MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
ICLR 2025
ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
CVPR 2025
SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation
ICCV 2025
TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
CVPR 2025
Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
CVPR 2025
AutoPSV: Automated Process-Supervised Verifier
NeurIPS 2024
Disentangled Clothed Avatar Generation from Text Descriptions
ECCV 2024
"EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation"
ECCV 2024
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
ECCV 2024
TLControl: Trajectory and Language Control for Human Motion Synthesis
ECCV 2024
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
CVPR 2024
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer
ICCV 2023