Jiaxin Zhang

papers

323

total citations

papers (11)

Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage

CVPR 2022arXiv

159

citations

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

ICCV 2023arXiv

citations

DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming

AAAI 2025arXiv

citations

COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting

CVPR 2025arXiv

citations

Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

ICLR 2025arXiv

citations

Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

NEURIPS 2023arXiv

citations

M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis

CVPR 2023

citations

On the Stochastic Stability of Deep Markov Models

NEURIPS 2021

citations

Jiaxin Zhang

papers (11)

Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming

DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

UPOCR: Towards Unified Pixel-Level OCR Interface

COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting

Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis

On the Stochastic Stability of Deep Markov Models

papers (11)

Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming

DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler

UPOCR: Towards Unified Pixel-Level OCR Interface

COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting

Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis

On the Stochastic Stability of Deep Markov Models