CX
Chang Xu
cs.CVcs.LGcs.AIstat.MLcs.CLcs.ROeess.IVNeural Networks, Computercs.CRAlgorithms
On Valency
published · living versionsW_ejap66t4·v1 · currentpublished
PASA-KV: Attacking Action-Facing Visual Routes in World Action Models
with Zhongbo Wu, Jiakai Huang, Zheng Zhang, Siyu Xu +4
1 version
W_hbmkqura·v1published
W_8kvbcqda·v1published
Preprints & journals
214 papers in the corpus · 2011–2026High Frame Rate iToF-Flow-Based Depth Imaging Enabled by Local Linear Transfer.42574417 · Meng, Yu, Xue, Zhou, Chang, Xu et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(11):15470-15487
Region-Level Policy Optimization for Fine-grained MLLM Perception2609.19745v1 · Yuheng Shi, Xiaohuan Pei, Minjing Dong et al.2026 · 0 citationsarXiv
RA-SOD: Reliability-Aware RGB-T Salient Object Detection under Modality Degradation2609.12622v1 · Hongbo Gao, Zhengyu Li, Xueru Nie et al.2026 · 0 citationsarXivon Valency
Improved Residual Learning in Diffusion Models.42081429 · Zhang, Junyu, Liu, Daochang, Park, Eunbyung et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(9):10991-11006
OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction2608.16499v3 · Hongbo Gao, Wei Zhang, Zeyu Ni et al.2026 · 0 citationsarXiv
StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models2608.11671v1 · Siyu Xu, Yunke Wang, Zijian Wang et al.2026 · 0 citationsarXiv
LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration2608.12032v1 · Enhuai Liu, Yunke Wang, Yutong Wang et al.2026 · 0 citationsarXiv
Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation2606.31382v1 · Fengnian Zhang, Tao Huang, Siyu Xu et al.2026 · 0 citationsarXiv
Multidimensional motivation in aging: a validated framework spanning goal-directed behaviour, social reward and pleasure10.64898/2026.06.11.26355497v2 · Warren, S. L., Somasundaram, H., Horne, K. et al.2026 · 1 citationmedRxiv
BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation2605.27067v2 · Yutong Wang, Yunke Wang, Xinyuan Chen et al.2026 · 0 citationsarXiv
PARE: Pruning and Adaptive Routing for Efficient Video Generation2605.27336v1 · Yutong Wang, Yunke Wang, Tianfan Xue et al.2026 · 0 citationsarXiv
Adversarial Error Correction for Visual Autoregressive Generation2605.24843v1 · Ligong Bi, Tao Huang, Jianyuan Guo et al.2026 · 0 citationsarXiv
Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation2605.13122v2 · Jingxuan He, Xiyu Wang, Yunke Wang et al.2026 · 0 citationsarXiv
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model2605.11817v2 · Yixu Feng, Zinan Zhao, Yanxiang Ma et al.2026 · 0 citationsProceedings of the Forty-third International Conference on Machine Learning, 2026
UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection2605.07146v1 · Laibin Chang, Shaodong Wang, Yunke Wang et al.2026 · 0 citationsarXiv
Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation2605.02757v1 · Chenyu Hui, Xiaodi Huang, Siyu Xu et al.2026 · 0 citationsarXiv
Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models2604.06912v1 · Yuheng Shi, Xiaohuan Pei, Linfeng Wen et al.2026 · 0 citationsarXiv
Prepare to Turn: Learning Anticipatory Maneuvering for Fast Sequential Quadrupedal Navigation2603.12842v3 · Zunzhi You, Yunke Wang, Haolan Guo et al.2026 · 0 citationsarXiv
Design and simulation of the High-Energy Proton Beam Telescope2602.13982v1 · Lan-Kun Li, Ze Gao, Ying-Hao Yu et al.2026 · 0 citationsarXiv
Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations2601.13534v3 · Xu Zhang, Junwei Deng, Chang Xu et al.2026 · 0 citationsarXiv
ChatAD: Reasoning-Enhanced Time-Series Anomaly Detection with Multi-Turn Instruction Evolution2601.13546v1 · Hui Sun, Chang Xu, Haonan Xie et al.2026 · 0 citationsarXiv
Toward Effective Knowledge Distillation: Navigating Beyond Small-Data Pitfall.40924515 · Hao, Zhiwei, Guo, Jianyuan, Han, Kai et al.2025 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(1):542-556
Marine Saliency Segmenter: Object-Focused Conditional Diffusion With Region-Level Semantic Knowledge Distillation.42241268 · Chang, Laibin, Wang, Yunke, Huang, Jiaxing et al.2026 · 2 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;35:6789-6800
MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow.42579591 · Li, Zhe, He, Yisheng, Zhong, Lei et al.2026 · 0 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2026;35:8719-8733
RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion2512.23649v5 · Zhe Li, Boan Zhu, Yangyang Wei et al.2025 · 0 citationsarXiv
Large language models driven neural architecture search for universal and lightweight disease diagnosis on histopathology slide images.41254215 · Su, Xiu, Mao, Qinghua, Wu, Zhongze et al.2025 · 2 citationsNPJ digital medicine. 2025;8(1):682
SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning2510.22534v1 · Chen Chen, Majid Abdolshah, Violetta Shevchenko et al.2025 · 0 citationsarXiv
Graph Unlearning Meets Influence-aware Negative Preference Optimization2510.19479v1 · Qiang Chen, Zhongze Wu, Ang He et al.2025 · 1 citationarXiv
From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance2510.14952v2 · Zhe Li, Cheng Chi, Yangyang Wei et al.2025 · 0 citationsarXiv
Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding2510.06308v1 · Yi Xin, Qi Qin, Siqi Luo et al.2025 · 0 citationsarXiv
Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance2509.23876v3 · Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh et al.2025 · 0 citationsarXiv
Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation2509.22093v1 · Xiaohuan Pei, Yuxing Chen, Siyu Xu et al.2025 · 0 citationsarXiv
DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training2509.14642v1 · Yuemin Wu, Zhongze Wu, Xiu Su et al.2025 · 0 citationsarXiv
MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field.39378248 · Yang, Zijiang, Qiu, Zhongwei, Xu, Chang et al.2025 · 3 citationsIEEE transactions on visualization and computer graphics. 2025;31(9):5842-5853
Identify, Isolate, and Purge: Mitigating Hallucinations in LVLMs via Self-Evolving Distillation2507.04680v2 · Wenhao Li, Xiu Su, Jingyi Wu et al.2025 · 0 citationsarXiv
DIST+: Knowledge Distillation From a Stronger Adaptive Teacher.40138231 · Huang, Tao, You, Shan, Wang, Fei et al.2025 · 26 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(7):5571-5585
Rethinking Causal Mask Attention for Vision-Language Inference2505.18605v1 · Xiaohuan Pei, Tao Huang, YanXiang Ma et al.2025 · 0 citationsarXiv
Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models2504.18032v1 · Chen Chen, Daochang Liu, Mubarak Shah et al.2025 · 2 citationsarXiv
Adversarially Robust Neural Architectures.40036408 · Dong, Minjing, Li, Yanxi, Wang, Yunhe et al.2025 · 46 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(5):4183-4197
Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study2503.06794v4 · Yizheng Sun, Hao Li, Chang Xu et al.2025 · 0 citationsarXiv
Learning Mask Invariant Mutual Information for Masked Image Modeling2502.19718v1 · Tao Huang, Yanxiang Ma, Shan You et al.2025 · 0 citationsarXiv
VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching2502.02175v2 · Siyu Xu, Yunke Wang, Chenghao Xia et al.2025 · 13 citationsarXiv
Color Correction Meets Cross-Spectral Refinement: A Distribution-Aware Diffusion for Underwater Image Restoration2501.04740v1 · Laibin Chang, Yunke Wang, Bo Du et al.2025 · 12 citationsarXiv
Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection2412.13732v2 · Kun Yan, Zied Bouraoui, Fangyun Wei et al.2024 · 3 citationsarXiv
Cross-Self KV Cache Pruning for Efficient Vision-Language Inference2412.04652v1 · Xiaohuan Pei, Tao Huang, Chang Xu2024 · 0 citationsarXiv
UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping2412.02699v2 · Wenbo Wang, Fangyun Wei, Lei Zhou et al.2024 · 10 citationsarXiv
Learning Visual Abstract Reasoning through Dual-Stream Networks2411.19451v1 · Kai Zhao, Chang Xu, Bailu Si2024 · 9 citationsProceedings of the AAAI Conference on Artificial Intelligence, 38(15), 16979-16988
DiffAct++: Diffusion Action Segmentation.40030562 · Liu, Daochang, Li, Qiyue, Dinh, Anh-Dung et al.2025 · 14 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;PP
Weak Augmentation Guided Relational Self-Supervised Learning.38809743 · Zheng, Mingkai, You, Shan, Wang, Fei et al.2024 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):8502-8516
Exploring Local Memorization in Diffusion Models via Bright Ending Attention2410.21665v2 · Chen Chen, Daochang Liu, Mubarak Shah et al.2024 · 0 citationsarXiv
Career total: at least 438 works. 214 are in this corpus.Showing the 50 most recent.
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.