XW
Xingjiao Wu
cs.CVcs.AIcs.CLcs.LGcs.HCadaptive learningcontrastive learningconvolutional neural networkcrowd countingcs.MA
On Valency
published · living versionsW_7snpe3wj·v1 · currentpublished
EviDial: When Correct Depression Predictions Lack Evidence
with Junjie Xu, Jin Zhu, Yuzhe Yang, Luhan Wang +4
1 version
Preprints & journals
37 papers in the corpus · 2018–2026HealBench: A Fine-Grained Benchmark for Evaluating Psychological Comfort in Text-to-Image Generation2610.27516v1 · Junjie Xu, Yuzhe Yang, Rui Yang et al.2026 · 0 citationsarXivon Valency
EviDial: When Correct Depression Predictions Lack Evidence2610.27541v1 · Junjie Xu, Jin Zhu, Yuzhe Yang et al.2026 · 0 citationsarXivon Valency
Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents2606.04815v2 · Bo Mao, Jie Zhou, Yutao Yang et al.2026 · 0 citationsarXiv
Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaboration2606.18259v1 · Junjie Xu, Xingjiao Wu, Zihao Zhang et al.2026 · 0 citationsarXiv
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models2602.21704v1 · Jianghao Yin, Qin Chen, Kedi Chen et al.2026 · 0 citationsarXiv
APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation2601.06574v1 · Dongliang Chen, Xinlin Zhuang, Junjie Xu et al.2026 · 0 citationsarXiv
Large Language Models have Chain-of-Affect2512.12283v2 · Junjie Xu, Xingjiao Wu, Luwei Xiao et al.2025 · 0 citationsarXiv
Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations2509.12661v1 · Yougen Zhou, Qin Chen, Ningning Zhou et al.2025 · 0 citationsarXiv
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning2509.12958v2 · Bihao Zhan, Jie Zhou, Junsong Li et al.2025 · 0 citationsarXiv
A Dual-Encoder Contrastive Learning Model for Knowledge Tracing.40724402 · Bai, Yanhong, Wu, Xingjiao, Wei, Tingjiang et al.2025 · 4 citationsEntropy (Basel, Switzerland). 2025;27(7)
RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation2505.24442v1 · Zhentao Xie, Chengcheng Han, Jinxin Shi et al.2025 · 2 citationsarXiv
Task-Core Memory Management and Consolidation for Long-term Continual Learning2505.09952v1 · Tianyu Huai, Jie Zhou, Yuxuan Cai et al.2025 · 0 citationsarXiv
CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering2503.00413v1 · Tianyu Huai, Jie Zhou, Xingjiao Wu et al.2025 · 22 citationsarXiv
Aesthetic Matters in Music Perception for Image Stylization: A Emotion-driven Music-to-Visual Manipulation2501.01700v1 · Junjie Xu, Xingjiao Wu, Tanren Yao et al.2025 · 0 citationsarXiv
MindScope: Exploring cognitive biases in large language models through Multi-Agent Systems2410.04452v1 · Zhentao Xie, Jiabao Zhao, Yilei Wang et al.2024 · 4 citationsarXiv
Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences2409.07268v2 · Ziang Liu, Junjie Xu, Xingjiao Wu et al.2024 · 1 citationarXiv
Fine-Grained Scene Image Classification with Modality-Agnostic Adapter2407.02769v1 · Yiqun Wang, Zhao Zhou, Xiangcheng Du et al.2024 · 3 citationsarXiv
FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Models2405.03098v1 · Yanhong Bai, Jiabao Zhao, Jinxin Shi et al.2024 · 0 citationsarXiv
UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images2311.11306v2 · Weijie Li, Yitian Wan, Xingjiao Wu et al.2023 · 1 citationarXiv
DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding2310.18983v1 · Anran Wu, Luwei Xiao, Xingjiao Wu et al.2023 · 1 citationarXiv
Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering2310.09696v1 · Shuwen Yang, Anran Wu, Xingjiao Wu et al.2023 · 1 citationarXiv
CGMI: Configurable General Multi-Agent Interaction Framework2308.12503v2 · Shi Jinxin, Zhao Jiabao, Wang Yilei et al.2023 · 7 citationsarXiv
FairMonitor: A Four-Stage Automatic Framework for Detecting Stereotypes and Biases in Large Language Models2308.10397v2 · Yanhong Bai, Jiabao Zhao, Jinxin Shi et al.2023 · 0 citationsarXiv
DDT: Dual-branch Deformable Transformer for Image Denoising2304.06346v1 · Kangliang Liu, Xiangcheng Du, Sijie Liu et al.2023 · 23 citationsarXiv
LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion2303.03595v2 · Xin Li, Tao Ma, Yuenan Hou et al.2023 · 183 citationsarXiv
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection2210.09615v1 · Xin Li, Botian Shi, Yuenan Hou et al.2022 · 55 citationsarXiv
Progressive Scene Text Erasing with Self-Supervision2207.11469v2 · Xiangcheng Du, Zhao Zhou, Yingbin Zheng et al.2022 · 13 citationsarXiv
Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis2201.10274v1 · Luwei Xiao, Xingjiao Wu, Wen Wu et al.2022 · 49 citationsarXiv
Cross-Domain Document Layout Analysis Using Document Style Guide2201.09407v2 · Xingjiao Wu, Luwei Xiao, Xiangcheng Du et al.2022 · 6 citationsarXiv
Document Layout Analysis with Aesthetic-Guided Image Augmentation2111.13809v1 · Tianlong Ma, Xingjiao Wu, Xin Li et al.2021 · 2 citationsarXiv
Human-In-The-Loop Document Layout Analysis2108.02095v1 · Xingjiao Wu, Tianlong Ma, Xin Li et al.2021 · 2 citationsarXiv
A Survey of Human-in-the-loop for Machine Learning2108.00941v3 · Xingjiao Wu, Luwei Xiao, Yixuan Sun et al.2021 · 731 citationsFuture Generation Computer Systems,2022
Document Layout Analysis via Dynamic Residual Feature Fusion2104.02874v1 · Xingjiao Wu, Ziling Hu, Xiangcheng Du et al.2021 · 17 citationsIEEE ICME 2021 ORAL
Counting Crowds with Perspective Distortion Correction via Adaptive Learning.32640552 · Sun, Yixuan, Jin, Jian, Wu, Xingjiao et al.2020 · 4 citationsSensors (Basel, Switzerland). 2020;20(13)
Scene Text Recognition with Temporal Convolutional Encoder1911.01051v2 · Xiangcheng Du, Tianlong Ma, Yingbin Zheng et al.2019 · 10 citationsIEEE ICASSP 2020
Fast Video Crowd Counting with a Temporal Aware Network1907.02198v2 · Xingjiao Wu, Baohan Xu, Yingbin Zheng et al.2019 · 49 citationsNeurocomputing 2020
Adaptive Scenario Discovery for Crowd Counting1812.02393v2 · Xingjiao Wu, Yingbin Zheng, Hao Ye et al.2018 · 51 citationsIEEE ICASSP 2019
Career total: 102 works. 37 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.