GenShield: Unified Detection and Artifact Correction for AI-Generated Images

Zhipei Xu#, Xuanyu Zhang#, Youmin Xu#, Qing Huang, Shen Chen, Taiping Yao, Shouhong Ding, Jian Zhang
ICML 2026
Paper | Code
We propose GenShield, a unified autoregressive framework that jointly performs explainable AI-generated image detection and controllable artifact correction in a closed loop from diagnosis to restoration, built on a Mixture-of-Transformers architecture with a Visual Chain-of-Thought curriculum learning strategy.

VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought

Xuanyu Zhang, Weiqi Li, Qunliang Xing, Jingfen Xie, Bin Chen, Junlin Li, Li Zhang, Jian Zhang, Shijie Zhao
IJCV
Paper
We propose VQ-Jarvis, a retrieval-augmented, all-in-one intelligent video restoration agent. VQ-Jarvis features sharp vision through a large-scale paired enhancement dataset and GRPO-aligned perception models, and fast thought via a hierarchical scheduling strategy that retrieves optimal restoration trajectories from a RAG library or performs greedy search for complex cases.

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

Shijie Zhao#, Xuanyu Zhang#, Bin Chen, Weiqi Li, Qunliang Xing, Kexin Zhang, Yan Wang, Junlin Li, Li Zhang, Jian Zhang, Tianfan Xue
ECCV 2026
Paper
We propose OARS, a process-aware online alignment framework for generative real-world image super-resolution, built on COMPASS, a MLLM-based reward model that evaluates the LR-to-SR transition by jointly modeling fidelity preservation and perceptual gain. OARS performs progressive online alignment from cold-start flow matching to full-reference and reference-free RL.

Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment

Shijie Zhao#, Xuanyu Zhang#, Weiqi Li, Junlin Li, Li Zhang, Tianfan Xue, Jian Zhang
ICLR 2026 Oral
Paper | Code | Model
We revisit the reasoning mechanism in MLLM-based IQA model and propose a CLIP-based lightweight image scorer RALI. We verifies that through RL training, MLLMs leverage their reasoning capability to convert redundant visual representations into compact, cross-domain aligned text representations. This conversion is the source of the generalization exhibited by these reasoning-based IQA models. RALI uses only about 4% of Q-Insight’s parameters and inference time, while achieving comparable accuracy.

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning

Xuanyu Zhang, Weiqi Li, Shijie Zhao, Junlin Li, Li Zhang, Jian Zhang
AAAI 2026 Oral
Paper | Code | Model | Social Media
We propose VQ-Insight, a novel reasoning-style VLM framework for AIGC video quality assessment. Our approach features: (1) a progressive video quality learning scheme; (2) the design of multi-dimension scoring rewards, preference comparison rewards, and temporal modeling rewards.

FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

Zhipei Xu#, Xuanyu Zhang#, Runyi Li, Zecheng Tang, Qing Huang, Jian Zhang
ICLR 2025
Project | Code
We propose the explainable IFDL task and design FakeShield, a multi-modal framework capable of evaluating image authenticity, generating tampered region masks, and providing a judgment basis based on pixel-level and image-level tampering clues.

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

Xuanyu Zhang, Jiarui Meng, Zhipei Xu, Shuzhou Yang, Yanmin Wu, Ronggang Wang, Jian Zhang
ICLR 2025
Paper | Code
We propose a SecureGS, a secure and efficient 3DGS steganography framework inspired by Scaffold-GS’s anchor point design and neural decoding.

OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking

Xuanyu Zhang, Zecheng Tang, Zhipei Xu, Runyi Li, Youmin Xu, Bin Chen, Feng Gao, Jian Zhang
CVPR 2025
Paper | Code
We propose OmniGuard, a novel augmented versatile watermarking approach that integrates proactive embedding with passive, blind extraction for robust copyright protection and tamper localization.

GS-Hider: Hiding Messages into 3D Gaussian Splatting

Xuanyu Zhang, Jiarui Meng, Runyi Li, Zhipei Xu, Yongbing Zhang, Jian Zhang
NeurIPS 2024
Paper | Code ｜ Project
We propose the first 3DGS steganography framework GS-Hider, which can hide an entire 3D scene or an image into the original 3D scene and accurately decode it from 3D Gaussians.

EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection

Xuanyu Zhang, Runyi Li, Jiwen Yu, Youmin Xu, Weiqi Li, Jian Zhang
CVPR 2024
Paper | Code | Project
We propose a versatile deep forensic watermark for AIGC editing methods, such as stable diffusion inpaint, controlnet, SDXL and etc.