Jinyang Zhang
About Me
I am an algorithm engineer focused on AIGC systems that connect research models with deployable workflows, with experience across speech-driven facial generation, digital human synthesis, face restoration, ComfyUI restoration workflows, and practical tools for model development and daily execution. I am currently seeking new opportunities where I can continue building reliable generative AI systems from research prototypes to usable products.
Publications
All publications-
IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration arXiv preprint arXiv:2605.02814 · 2026A unified reference-aware and no-reference face restoration framework that uses reliability-weighted identity anchors and degraded-image spatial structure anchors in one checkpoint.
-
The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results arXiv preprint arXiv:2604.10532v2 / CVPR 2026 Workshop · 2026NTIRE 2026 real-world face restoration challenge report covering task design, weighted IQA evaluation, identity checking, submitted methods, and final rankings.
-
Learning Discriminative Compact Representation for Hyperspectral Imagery Classification IEEE Transactions on Geoscience and Remote Sensing (TGRS) · 2019A multi-task deep network for hyperspectral image classification that jointly learns compact spectral representation, reconstruction, and pixelwise classification.
-
Improving Hyperspectral Image Classification with Unsupervised Knowledge Learning (IGARSS) IEEE International Geoscience and Remote Sensing Symposium · 2019Unsupervised knowledge learning for hyperspectral image classification, injecting clustering structure into supervised learning to improve generalization.
Projects
All projects-
Style-Talking 06/2026 · Zero-shot speaking-style clone for video-driven avatarsA zero-shot audio-driven digital human system that builds speaking-style prompts from a reference video, predicts LivePortrait expression motion from wav2vec audio features, and renders talking videos while preserving the original non-face regions.
-
Voice Studio 05/2026 · Local voice creation workspace for Apple Silicon MacsA local-first macOS voice creation app for premium voice generation, voice cloning, voice design, dialogue generation, and DeepSeek-assisted dialogue rewrite. It targets novels, audio drama, narration, character dialogue, and multi-role audio export workflows.
-
EfficientTime 05/2026 · Local-first AI daily planning assistantA local-first macOS productivity app for turning rough task notes into editable daily schedules. It keeps the current task visible and supports local reminders plus AI-assisted planning drafts.
-
3d-viewers 05/2026 · Browser viewers for 3D vision and digital-human modelsLightweight browser-based viewers for inspecting 3D vision and digital-human assets. It covers FLAME, parametric models, Gaussian avatars, topology, joints, bindings, and motion before fitting or training.
Foundations
All foundations-
LeetCode 热题 100 07/2026 · Python 题解与复杂度分析100 道 Hot100 题目的题意、分析、复杂度与 Python 解法
-
视频生成技术 07/2026 · Video VAE 到 Wan / LTXVideo VAE、DiT、Flow Matching、Wan、LTX、VACE、IC-LoRA 与音视频生成
-
图像生成技术 07/2026 · 数据、训练、RL 与蒸馏FLUX、Qwen-Image、Z-Image 的数据治理、训练、RL 与蒸馏