papers

Publications (18)

cs.CV2022

Safe Self-Refinement for Transformer-based Domain Adaptation

Tao Sun, Cheng Lu, Tianshuo Zhang +1

Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a…

cs.CV2026

Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection

Tianshuo Zhang, Haoyuan Zhang, Siran Peng +3

Continual face forgery detection (CFFD) requires detectors to learn emerging forgery paradigms without forgetting previously seen manipulations. Existing CFFD methods commonly rely…

cs.LG2025

Floating-Body Hydrodynamic Neural Networks

Tianshuo Zhang, Wenzhe Zhai, Rui Yann +3

Fluid-structure interaction is common in engineering and natural systems, where floating-body motion is governed by added mass, drag, and background flows. Modeling these dissipati…

cs.CV2024

S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketch

Zidu Wang, Xiangyu Zhu, Jiang Yu +2

3D textured face reconstruction from sketches applicable in many scenarios such as animation, 3D avatars, artistic design, missing people search, etc., is a highly promising but un…

cs.CL2026

Self-Supervised Skill Optimization

Siran Peng, Cuiyu Yang, Tianyu Fu +9

Agent skills provide frozen large language model (LLM) agents with reusable procedural guidance, and recent work shows that such skills can be optimized with ground-truth (GT) feed…

cs.CV2026

From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing

Haoyuan Zhang, Keyao Wang, Guosheng Zhang +11

Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FAS) solutions. Recent MLLM-based FAS methods reformulate the binary classificat…

cs.CV2024

3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation

Zidu Wang, Xiangyu Zhu, Tianshuo Zhang +2

3D Morphable Models (3DMMs) provide promising 3D face reconstructions in various applications. However, existing methods struggle to reconstruct faces with extreme expressions due…

cs.CV2025

WMamba: Wavelet-based Mamba for Face Forgery Detection

Siran Peng, Tianshuo Zhang, Li Gao +4

The rapid evolution of deepfake generation technologies necessitates the development of robust face forgery detection algorithms. Recent studies have demonstrated that wavelet anal…

cs.LG2025

Shackled Dancing: A Bit-Locked Diffusion Algorithm for Lossless and Controllable Image Steganography

Tianshuo Zhang, Gao Jia, Wenzhe Zhai +2

Data steganography aims to conceal information within visual content, yet existing spatial- and frequency-domain approaches suffer from trade-offs between security, capacity, and p…

cs.CL2026

One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry

Weisong Zhao, Tong Wang, Zichang Tan +11

Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO. While GMPO improves stability by constraining a conservative objectiv…

cs.CV2025

DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces

Tianshuo Zhang, Li Gao, Siran Peng +2

The rise of realistic digital face generation and manipulation poses significant social risks. The primary challenge lies in the rapid and diverse evolution of generation technique…

cs.CV2026

Private Face Recognition Training Dataset Publication via Identity-Decoupled and Geometry-Preserving Face Distillation

Shuhuan Chen, Xiangyu Zhu, Weisong Zhao +6

The paper proposes a method to publish face recognition training datasets that removes personal identity information while keeping the geometric relationships needed for effective…

#privacy-preserving face recognition#dataset publishing#identity decoupling#geometry preservation
cs.CV2022

Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation

Changwei Xu, Jianfei Yang, Haoran Tang +3

Unsupervised Domain Adaptation (UDA), a branch of transfer learning where labels for target samples are unavailable, has been widely researched and developed in recent years with t…

cs.CV2025

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization

Siran Peng, Haoyuan Zhang, Li Gao +5

The rapid evolution of deepfake technologies demands robust and reliable face forgery detection algorithms. While determining whether an image has been manipulated remains essentia…

cs.CV2025

Unifying Locality of KANs and Feature Drift Compensation Projection for Data-free Replay based Continual Face Forgery Detection

Tianshuo Zhang, Siran Peng, Li Gao +3

The rapid advancements in face forgery techniques necessitate that detectors continuously adapt to new forgery methods, thus situating face forgery detection within a continual lea…

cs.CV2025

SemiOccam: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels

Rui Yann, Tianshuo Zhang, Xianglei Xing

We present SemiOccam, an image recognition network that leverages semi-supervised learning in a highly efficient manner. Existing works often rely on complex training techniques an…

cs.CV2025

MLLM-Enhanced Face Forgery Detection: A Vision-Language Fusion Solution

Siran Peng, Zipei Wang, Li Gao +5

Reliable face forgery detection algorithms are crucial for countering the growing threat of deepfake-driven disinformation. Previous research has demonstrated the potential of Mult…

cs.CL2026

UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection

Siran Peng, Weisong Zhao, Tianyu Fu +6

Prompt agents have recently emerged as a promising paradigm for automated prompt optimization, framing prompt discovery as a sequential decision-making problem over a structured pr…