CS
Chunhua Shen
cs.CVcs.LGcs.AIAlgorithmsstat.MLcs.CLArtificial Intelligenceeess.IVNeural Networks, Computercs.CE
On Valency
published · living versionsW_svgzshv6·v1 · currentpublished
Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy
with Yifei Yao, Yude Zou, Guanbo Jiao, Xing Gao +10
1 version
W_xdckp5ck·v1published
Preprints & journals
414 papers in the corpus · 2003–2026Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes2609.25841v1 · Yuling Xi, Haokai Zhang, Muzhi Zhu et al.2026 · 0 citationsarXiv
ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction2608.20920v2 · Linhao Zhong, Zongze Du, Linyu Wu et al.2026 · 0 citationsarXiv
Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization2512.00748v2 · Ke Liu, Shangde Gao, Yichao Fu et al.2025 · 0 citationsarXiv
RSeg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection2511.12691v1 · Shuaike Shen, Ke Liu, Jiaqing Xie et al.2025 · 0 citationsarXiv
Learning Dual-Stream Conditional Concepts in Compositional Zero-Shot Learning.40857183 · Wang, Qingsheng, Liu, Lingqiao, Jing, Chenchen et al.2025 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):10076-10093
StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation2510.05057v2 · Mingyu Liu, Jiuhe Shu, Hui Chen et al.2025 · 0 citationsarXiv
DMark: Order-Agnostic Watermarking for Diffusion Large Language Models2510.02902v1 · Linyu Wu, Linhao Zhong, Wenjie Qu et al.2025 · 0 citationsarXiv
HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation2509.23736v1 · Cong Chen, Ziyuan Huang, Cheng Zou et al.2025 · 0 citationsarXiv
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling2509.12201v2 · Yang Zhou, Yifan Wang, Jianjun Zhou et al.2025 · 0 citationsarXiv
Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization2508.14811v1 · Canyu Zhao, Xiaoman Li, Tianjian Feng et al.2025 · 0 citationsarXiv
Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models2508.09138v3 · Wen Wang, Bozhen Fang, Chenchen Jing et al.2025 · 0 citationsarXiv
Generative Video Matting2508.07905v1 · Yongtao Ge, Kangyang Xie, Guangkai Xu et al.2025 · 1 citationSIGGRAPH Conference Papers 2025
Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection2508.01591v2 · Hanxi Li, Jingqi Wu, Lin Yuanbo Wu et al.2025 · 0 citationsarXiv
PonderV2: Improved 3D Representation With a Universal Pre-Training Paradigm.40249676 · Zhu, Haoyi, Yang, Honghui, Wu, Xiaoyang et al.2025 · 3 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(8):6550-6565
SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting2507.15602v2 · Zihui Gao, Jia-Wang Bian, Guosheng Lin et al.2025 · 2 citationsarXiv
: Permutation-Equivariant Visual Geometry Learning2507.13347v3 · Yifan Wang, Jianjun Zhou, Haoyi Zhu et al.2025 · 2 citationsarXiv
When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators2506.19348v2 · Jintao Rong, Xin Xie, Xinyi Yu et al.2025 · 0 citationsarXiv
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning2505.21457v2 · Muzhi Zhu, Hao Zhong, Canyu Zhao et al.2025 · 0 citationsarXiv
MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning2503.18533v1 · Dawei Yan, Yang Li, Qing-Guo Chen et al.2025 · 0 citationsarXiv
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories2503.08625v1 · Muzhi Zhu, Yuzhuo Tian, Hao Chen et al.2025 · 5 citationsarXiv
VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization.40031074 · Liu, Yuliang, Huang, Mingxin, Yan, Hao et al.2025 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(4):2957-2972
Revisiting Convolution Architecture in the Realm of DNA Foundation Models2502.18538v1 · Yu Bo, Weian Mao, Yanjun Shao et al.2025 · 0 citationsarXiv
REO-VLM: Transforming VLM to Meet Regression Challenges in Earth Observation2412.16583v1 · Xizhe Xue, Guoting Wei, Hao Chen et al.2024 · 2 citationsarXiv
MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation2411.15262v2 · Weijia Wu, Mingyu Liu, Zeyu Zhu et al.2024 · 7 citationsCVPR 2025
Self-Supervised 3D Scene Flow Estimation and Motion Prediction Using Local Rigidity Prior.38743546 · Li, Ruibo, Zhang, Chi, Wang, Zhe et al.2024 · 4 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):8106-8122
Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation.39150798 · Hu, Mu, Yin, Wei, Zhang, Chi et al.2024 · 263 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):10579-10596
Framer: Interactive Frame Interpolation2410.18978v2 · Wen Wang, Qiuyu Wang, Kecheng Zheng et al.2024 · 0 citationsarXiv
Depth Any Video with Scalable Synthetic Data2410.10815v2 · Honghui Yang, Di Huang, Wei Yin et al.2024 · 0 citationsarXiv
Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions2410.09543v1 · Xiaoran Jiao, Weian Mao, Wengong Jin et al.2024 · 1 citationarXiv
A Simple Image Segmentation Framework via In-Context Examples2410.04842v2 · Yang Liu, Chenchen Jing, Hengtao Li et al.2024 · 7 citationsarXiv
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation2410.02369v3 · Muzhi Zhu, Yang Liu, Zekai Luo et al.2024 · 13 citationsarXiv
TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings2409.09564v2 · Dawei Yan, Pengcheng Li, Yang Li et al.2024 · 3 citationsarXiv
MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence2407.16655v3 · Canyu Zhao, Mingyu Liu, Wen Wang et al.2024 · 1 citationarXiv
Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization2407.03130v2 · Hanxi Li, Jingqi Wu, Lin Yuanbo Wu et al.2024 · 1 citationarXiv
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models2406.12671v2 · Yongtao Ge, Guangkai Xu, Zhiyue Zhao et al.2024 · 0 citationsarXiv
Generative Active Learning for Long-tailed Instance Segmentation2406.02435v1 · Muzhi Zhu, Chengxiang Fan, Hao Chen et al.2024 · 2 citationsarXiv
On the Trajectory Regularity of ODE-based Diffusion Sampling2405.11326v1 · Defang Chen, Zhenyu Zhou, Can Wang et al.2024 · 0 citationsarXiv
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data2405.10185v1 · Chengxiang Fan, Muzhi Zhu, Hao Chen et al.2024 · 8 citationsarXiv
Zippo: Zipping Color and Transparency Distributions into a Single Diffusion Model2403.11077v2 · Kangyang Xie, Binbin Yang, Hao Chen et al.2024 · 0 citationsarXiv
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?2403.06090v4 · Guangkai Xu, Yongtao Ge, Mingyu Liu et al.2024 · 1 citationarXiv
VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks2403.00522v2 · Xiangxiang Chu, Jianlin Su, Bo Zhang et al.2024 · 19 citationsarXiv
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model2402.03766v1 · Xiangxiang Chu, Limeng Qiao, Xinyu Zhang et al.2024 · 10 citationsarXiv
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices2312.16886v2 · Xiangxiang Chu, Limeng Qiao, Xinyang Lin et al.2023 · 13 citationsarXiv
GenDeF: Learning Generative Deformation Field for Video Generation2312.04561v1 · Wen Wang, Kecheng Zheng, Qiuyu Wang et al.2023 · 0 citationsarXiv
SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes.37801376 · Sun, Libo, Bian, Jia-Wang, Zhan, Huangying et al.2023 · 107 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(1):497-508
Paragraph-to-Image Generation with Information-Enriched Diffusion Model2311.14284v3 · Weijia Wu, Zhuang Li, Yefei He et al.2023 · 11 citationsIJCV 2025
AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort2311.11243v1 · Wen Wang, Canyu Zhao, Hao Chen et al.2023 · 3 citationsarXiv
SPTS v2: Single-Point Scene Text Spotting.37669204 · Liu, Yuliang, Zhang, Jiaxin, Peng, Dezhi et al.2023 · 55 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(12):15665-15679
Learning From Partially Labeled Data for Multi-Organ and Tumor Segmentation.37672381 · Xie, Yutong, Zhang, Jianpeng, Xia, Yong et al.2023 · 42 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(12):14905-14919
RGM: A Robust Generalizable Matching Model2310.11755v4 · Songyan Zhang, Xinyu Sun, Hao Chen et al.2023 · 0 citationsarXiv
Career total: 634 works. 414 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.