Publications (28)
Dataset Distillation via Committee Voting
Jiacheng Cui, Zhaoyi Li, Xiaochen Ma +3
Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction
Bo Du, Xiaochen Ma, Xuekang Zhu +8
Towards Next-Generation LLM Training: From the Data-Centric Perspective
Hao Liang, Zhengyang Zhao, Zhaoyang Han +8
Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization
Xuekang Zhu, Xiaochen Ma, Lei Su +7
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
Lu Ma, Hao Liang, Meiyi Qiang +9
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Hao Liang, Xiaochen Ma, Zhou Liu +32
Ordeal Mechanisms, Information, and the Cost-Effectiveness of Subsidies: Evidence from Subsidized Eyeglasses in Rural China
Sean Sylvia, Xiaochen Ma, Yaojiang Shi +2
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
Hao Liang, Qifeng Cai, Yibo Lin +11
IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer
Xiaochen Ma, Bo Du, Zhuohang Jiang +3
DINOv3 Beats Specialized Detectors: A Simple Foundation Model Baseline for Image Forensics
Jieming Yu, Qiuxiao Feng, Zhuohan Wang +1
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
Hao Liang, Qihan Lin, Zhaoyang Han +5
Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer
Lei Su, Xiaochen Ma, Xuekang Zhu +3
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
Xiaochen Ma, Xuekang Zhu, Lei Su +8
Perceptual MAE for Image Manipulation Localization: A High-level Vision Learner Focusing on Low-level Features
Xiaochen Ma, Jizhe Zhou, Xiong Xu +2
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Yuran Wang, Bohan Zeng, Chengzhuo Tong +6
Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
Bohan Zeng, Kaixin Zhu, Daili Hua +24
Coupling Methods and Applications on Path Dependent McKean-Vlasov SDEs
Xing Huang, Xiaochen Ma
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
Bo Du, Xuekang Zhu, Xiaochen Ma +6
Pre-training-free Image Manipulation Localization through Non-Mutually Exclusive Contrastive Learning
Jizhe Zhou, Xiaochen Ma, Xia Du +2
Harnack Inequality for Distribution Dependent Stochastic Hamiltonian System
Xing Huang, Xiaochen Ma
GReS: Graphical Cross-domain Recommendation for Supply Chain Platform
Zhiwen Jing, Ziliang Zhao, Yang Feng +6
M^3:Manipulation Mask Manufacturer for Arbitrary-Scale Super-Resolution Mask
Xinyu Yang, Xiaochen Ma, Xuekang Zhu +5
Extrinsic derivatives for SDEs and SPDEs with distribution dependent noise
Xiaochen Ma, Panpan Ren
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
DataFlow Team, Bohan Zeng, Daili Hua +39
GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization
Zhengyang Zhao, Lu Ma, Yizhen Jiang +7
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Runming He, Zhen Hao Wong, Hao Liang +4
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Yifan Dai, Zhenhua Wu, Bohan Zeng +18