wovepaper — the arXiv observatory

papers

Publications (17)

Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking

Yuchi Liu, Zhongdao Wang, Xiangxin Zhou +1

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

Boosting Semi-Supervised Face Recognition with Noise Robustness

Yuchi Liu, Hailin Shi, Hang Du +4

Assessing Model Generalization in Vicinity

Yuchi Liu, Yifan Sun, Jingdong Wang +1

Semi-Siamese Training for Shallow Face Learning

Hang Du, Hailin Shi, Yuchi Liu +4

An Improved Lightweight YOLOv5 Model Based on Attention Mechanism for Face Mask Detection

Sheng Xu, Zhanyu Guo, Yuchi Liu +2

Optimizing Calibration by Gaining Aware of Prediction Correctness

Yuchi Liu, Lei Wang, Yuli Zou +2

Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization

Yuchi Liu, Jaskirat Singh, Gaowen Liu +2

How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?

Yuchi Liu, Zhongdao Wang, Tom Gedeon +1

Imagen 3

Imagen-Team-Google, :, Jason Baldridge +257

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning

Zhu Xu, Zhiqiang Zhao, Zihan Zhang +6

MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale

Zhicong Tang, Zhao Zhang, Jingye Chen +6

A Utility-preserving De-identification Pipeline for Cross-hospital Radiology Data Sharing

Chenhao Liu, Zelin Wen, Yan Tong +7

Harm Amplification in Text-to-Image Models

Susan Hao, Renee Shelby, Yuchi Liu +6

ShieldGemma 2: Robust and Tractable Image Content Moderation

Wenjun Zeng, Dana Kurniawan, Ryan Mullins +14

ShieldGemma: Generative AI Content Moderation Based on Gemma

Wenjun Zeng, Yuchi Liu, Ryan Mullins +9

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization

Zhixin Lin, Jungang Li, Dongliang Xu +5