Picture for Mingze Sun

Mingze Sun

ARMO: Autoregressive Rigging for Multi-Category Objects

Add code
Mar 26, 2025
Viaarxiv icon

MOAT: Evaluating LMMs for Capability Integration and Instruction Grounding

Add code
Mar 12, 2025
Viaarxiv icon

DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters

Add code
Nov 26, 2024
Figure 1 for DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
Figure 2 for DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
Figure 3 for DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
Figure 4 for DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
Viaarxiv icon

SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation

Add code
Sep 18, 2024
Figure 1 for SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation
Figure 2 for SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation
Figure 3 for SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation
Figure 4 for SRIF: Semantic Shape Registration Empowered by Diffusion-based Image Morphing and Flow Estimation
Viaarxiv icon

Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony

Add code
Aug 18, 2024
Figure 1 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Figure 2 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Figure 3 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Figure 4 for Combo: Co-speech holistic 3D human motion generation and efficient customizable adaptation in harmony
Viaarxiv icon

Beyond Talking -- Generating Holistic 3D Human Dyadic Motion for Communication

Add code
Mar 28, 2024
Viaarxiv icon

FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio

Add code
Mar 04, 2024
Figure 1 for FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
Figure 2 for FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
Figure 3 for FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
Figure 4 for FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
Viaarxiv icon

Non-Rigid Shape Registration via Deep Functional Maps Prior

Add code
Nov 08, 2023
Figure 1 for Non-Rigid Shape Registration via Deep Functional Maps Prior
Figure 2 for Non-Rigid Shape Registration via Deep Functional Maps Prior
Figure 3 for Non-Rigid Shape Registration via Deep Functional Maps Prior
Figure 4 for Non-Rigid Shape Registration via Deep Functional Maps Prior
Viaarxiv icon

OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models

Add code
Oct 12, 2023
Figure 1 for OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models
Figure 2 for OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models
Figure 3 for OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models
Figure 4 for OpsEval: A Comprehensive Task-Oriented AIOps Benchmark for Large Language Models
Viaarxiv icon

Spatially and Spectrally Consistent Deep Functional Maps

Add code
Sep 05, 2023
Viaarxiv icon