Scholar
Li Chen
Google Scholar ID: vJXUa7MAAAAJ
ByteDance Inc.
Citations & Impact
Citations
1,969
H-index
17
i10-index
20
Publications
20
Co-authors
0
Resume
Academic Achievements
- XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation (NeurIPS 2025, Project Lead)
- PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models (NeurIPS 2025)
- AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose (AAAI 2024)
- SwiftAvatar: efficient auto-creation of parameterized stylized character on arbitrary avatar engines (AAAI 2023)
- Local and Global Logit Adjustments for Long-Tailed Learning (ICCV 2023)
- A data‐driven adversarial examples recognition framework via adversarial feature genomes (International Journal of Intelligent Systems, 2022)
- Scale-adaptive adversarial patch attack for remote sensing image aircraft detection (Remote Sensing, 2021)
- DAPnet: A double self-attention convolutional network for point cloud semantic labeling (IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021)
- Lie to me: A soft threshold defense method for adversarial examples of remote sensing images (IEEE Geoscience and Remote Sensing Letters, 2021)
- Estimation of the Potential Achievable Solar Energy of the Buildings Using Photogrammetric Mesh Models (Remote Sensing, 2021)
- An attention U-Net model for detection of fine-scale hydrologic streamlines (Environmental Modelling & Software, 2021)
- EFCNet: Ensemble Full Convolutional Network for Semantic Segmentation of High-Resolution Remote Sensing Images (IEEE Geoscience and Remote Sensing Letters, 2021)
- Contextual information-preserved architecture learning for remote-sensing scene classification (IEEE Transactions on Geoscience and Remote Sensing, 2021)
- A multiple subspaces-based model: Interpreting urban functional regions with big geospatial data (ISPRS International Journal of Geo-Information, 2021)
Research Experience
- Working as a Research Scientist at ByteDance, involved in intelligent creation.
Education
- Received Ph.D. from the School of Geosciences and Info-Physics, Central South University.
Background
- Currently a Research Scientist at ByteDance, focusing on CV, multimodal, and interpretability.