Xiaozhong Ji

xiaozhongji's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 6 papers 25 days ago

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

Paper • 2509.26165 • Published Sep 30, 2025

Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation

Paper • 2504.18087 • Published Apr 25, 2025 • 5

Sonic: Shifting Focus to Global Audio Perception in Portrait Animation

Paper • 2411.16331 • Published Nov 25, 2024 • 8

MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning

Paper • 2409.15179 • Published Sep 23, 2024

SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model

Paper • 2409.03270 • Published Sep 5, 2024

NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results

Paper • 2005.01996 • Published May 5, 2020

authored a paper 26 days ago

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

Paper • 2602.12705 • Published 30 days ago • 66

upvoted a paper 27 days ago

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

Paper • 2602.12705 • Published 30 days ago • 66

upvoted a paper 6 months ago

BaseReward: A Strong Baseline for Multimodal Reward Model

Paper • 2509.16127 • Published Sep 19, 2025 • 21

updated a model 6 months ago

xiaozhongji/qwen2_5_vl_7b_mmrl30k_grpo

Updated Sep 13, 2025

published a model 6 months ago

xiaozhongji/qwen2_5_vl_7b_mmrl30k_grpo

Updated Sep 13, 2025

upvoted a paper 9 months ago

MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs

Paper • 2506.01674 • Published Jun 2, 2025 • 28

authored a paper 10 months ago

HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

Paper • 2503.18860 • Published Mar 24, 2025 • 6

upvoted a paper 12 months ago

Sonic: Shifting Focus to Global Audio Perception in Portrait Animation

Paper • 2411.16331 • Published Nov 25, 2024 • 8

liked a Space about 1 year ago

Running on Zero

Featured

278

FitDiT

🦀

278

FitDiT is a high-fidelity virtual try-on model.

upvoted 2 papers over 1 year ago

FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on

Paper • 2411.10499 • Published Nov 15, 2024 • 13

Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement

Paper • 2411.06558 • Published Nov 10, 2024 • 36

authored a paper over 1 year ago

RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network

Paper • 2406.18284 • Published Jun 26, 2024 • 19

upvoted 2 papers over 1 year ago

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

Paper • 2407.02371 • Published Jul 2, 2024 • 55

RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network

Paper • 2406.18284 • Published Jun 26, 2024 • 19