Xuemiao Chen: Point Singularities and Local Third Chern Classes for Rank-Two Torsion-free Sheaves on Threefolds https://arxiv.org/abs/2607.01402 https://arxiv.org/pdf/2607.01402 https://arxiv.org/html/2607.01402
July 3, 2026 at 6:47 AM
Xuemiao Chen: Point Singularities and Local Third Chern Classes for Rank-Two Torsion-free Sheaves on Threefolds https://arxiv.org/abs/2607.01402 https://arxiv.org/pdf/2607.01402 https://arxiv.org/html/2607.01402
Yihan Zhou, Zikai Huang, Yuyang Yu, Xuemiao Xu, Cheng Xu, Shengfeng He: InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond https://arxiv.org/abs/2609.04903 https://arxiv.org/pdf/2609.04903 https://arxiv.org/html/2609.04903
September 7, 2026 at 6:40 AM
Yihan Zhou, Zikai Huang, Yuyang Yu, Xuemiao Xu, Cheng Xu, Shengfeng He: InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond https://arxiv.org/abs/2609.04903 https://arxiv.org/pdf/2609.04903 https://arxiv.org/html/2609.04903
Zikai Huang, Siyue Chen, Xuemiao Xu, Haoxin Yang, Cheng Xu, Yihong Lin, Shengfeng He: Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors https://arxiv.org/abs/2607.10313 https://arxiv.org/pdf/2607.10313 https://arxiv.org/html/2607.10313
July 14, 2026 at 6:41 AM
Zikai Huang, Siyue Chen, Xuemiao Xu, Haoxin Yang, Cheng Xu, Yihong Lin, Shengfeng He: Learn2Chat: Rethinking Dyadic Talking Heads via Interaction-Modulated Monologic Priors https://arxiv.org/abs/2607.10313 https://arxiv.org/pdf/2607.10313 https://arxiv.org/html/2607.10313
Xuemiao Xu, Maosheng Jiang, Jiansong Zhang, Jiang Zhu: A novel energy-conservation Crank-Nicolson finite element method for generalized Klein-Gordon-Zakharov equations https://arxiv.org/abs/2605.11686 https://arxiv.org/pdf/2605.11686 https://arxiv.org/html/2605.11686
May 13, 2026 at 6:49 AM
Xuemiao Xu, Maosheng Jiang, Jiansong Zhang, Jiang Zhu: A novel energy-conservation Crank-Nicolson finite element method for generalized Klein-Gordon-Zakharov equations https://arxiv.org/abs/2605.11686 https://arxiv.org/pdf/2605.11686 https://arxiv.org/html/2605.11686
Dijia Zhan, Jinyi Li, Chenxi Zheng, Shaoyu Huang, Yong Li, Jie Tang, Xuemiao Xu: NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps https://arxiv.org/abs/2605.06317 https://arxiv.org/pdf/2605.06317 https://arxiv.org/html/2605.06317
May 8, 2026 at 6:41 AM
Dijia Zhan, Jinyi Li, Chenxi Zheng, Shaoyu Huang, Yong Li, Jie Tang, Xuemiao Xu: NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps https://arxiv.org/abs/2605.06317 https://arxiv.org/pdf/2605.06317 https://arxiv.org/html/2605.06317
Chaohong Guo, Yihan He, Yongwei Nie, Fei Ma, Xuemiao Xu, Chengjiang Long: T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding https://arxiv.org/abs/2603.06973 https://arxiv.org/pdf/2603.06973 https://arxiv.org/html/2603.06973
March 10, 2026 at 6:31 AM
Chaohong Guo, Yihan He, Yongwei Nie, Fei Ma, Xuemiao Xu, Chengjiang Long: T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding https://arxiv.org/abs/2603.06973 https://arxiv.org/pdf/2603.06973 https://arxiv.org/html/2603.06973
Haoxin Yang, Yihong Lin, Jingdan Kang, Xuemiao Xu, Yue Li, Cheng Xu, Shengfeng He: Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization https://arxiv.org/abs/2510.24213 https://arxiv.org/pdf/2510.24213 https://arxiv.org/html/2510.24213
October 29, 2025 at 6:31 AM
Haoxin Yang, Yihong Lin, Jingdan Kang, Xuemiao Xu, Yue Li, Cheng Xu, Shengfeng He: Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization https://arxiv.org/abs/2510.24213 https://arxiv.org/pdf/2510.24213 https://arxiv.org/html/2510.24213
Guo Li, Yuyang Yu, Xuemiao Xu: Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models https://arxiv.org/abs/2510.21783 https://arxiv.org/pdf/2510.21783 https://arxiv.org/html/2510.21783
October 28, 2025 at 6:30 AM
Guo Li, Yuyang Yu, Xuemiao Xu: Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models https://arxiv.org/abs/2510.21783 https://arxiv.org/pdf/2510.21783 https://arxiv.org/html/2510.21783
Yuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang, Haoxin Yang, Yongwei Nie, Shengfeng He: Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection https://arxiv.org/abs/2510.16865 https://arxiv.org/pdf/2510.16865 https://arxiv.org/html/2510.16865
October 21, 2025 at 6:31 AM
Yuyang Yu, Zhengwei Chen, Xuemiao Xu, Lei Zhang, Haoxin Yang, Yongwei Nie, Shengfeng He: Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection https://arxiv.org/abs/2510.16865 https://arxiv.org/pdf/2510.16865 https://arxiv.org/html/2510.16865
Xiang Tuo, Xu Xuemiao, Liu Bangzhen, Li Jinyi, Li Yong, He Shengfeng: Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification https://arxiv.org/abs/2509.14958 https://arxiv.org/pdf/2509.14958 https://arxiv.org/html/2509.14958
September 19, 2025 at 6:30 AM
Xiang Tuo, Xu Xuemiao, Liu Bangzhen, Li Jinyi, Li Yong, He Shengfeng: Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification https://arxiv.org/abs/2509.14958 https://arxiv.org/pdf/2509.14958 https://arxiv.org/html/2509.14958
Chaohong Guo, Xun Mo, Yongwei Nie, Xuemiao Xu, Chao Xu, Fei Yu, Chengjiang Long: TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding https://arxiv.org/abs/2508.07683 https://arxiv.org/pdf/2508.07683 https://arxiv.org/html/2508.07683
August 12, 2025 at 6:32 AM
Chaohong Guo, Xun Mo, Yongwei Nie, Xuemiao Xu, Chao Xu, Fei Yu, Chengjiang Long: TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding https://arxiv.org/abs/2508.07683 https://arxiv.org/pdf/2508.07683 https://arxiv.org/html/2508.07683
Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, Shengfeng He: StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion https://arxiv.org/abs/2508.02056 https://arxiv.org/pdf/2508.02056 https://arxiv.org/html/2508.02056
August 5, 2025 at 6:32 AM
Haoxin Yang, Weihong Chen, Xuemiao Xu, Cheng Xu, Peng Xiao, Cuifeng Sun, Shaoyu Huang, Shengfeng He: StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion https://arxiv.org/abs/2508.02056 https://arxiv.org/pdf/2508.02056 https://arxiv.org/html/2508.02056
Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He: ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition https://arxiv.org/abs/2507.11261 https://arxiv.org/pdf/2507.11261 https://arxiv.org/html/2507.11261
July 16, 2025 at 6:31 AM
Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He: ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition https://arxiv.org/abs/2507.11261 https://arxiv.org/pdf/2507.11261 https://arxiv.org/html/2507.11261
Jingdan Kang, Haoxin Yang, Yan Cai, Huaidong Zhang, Xuemiao Xu, Yong Du, Shengfeng He: SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation https://arxiv.org/abs/2503.19791 https://arxiv.org/pdf/2503.19791 https://arxiv.org/html/2503.19791
March 26, 2025 at 6:08 AM
Jingdan Kang, Haoxin Yang, Yan Cai, Huaidong Zhang, Xuemiao Xu, Yong Du, Shengfeng He: SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation https://arxiv.org/abs/2503.19791 https://arxiv.org/pdf/2503.19791 https://arxiv.org/html/2503.19791
Weihong Chen, Xuemiao Xu, Haoxin Yang, Yi Xie, Peng Xiao, Cheng Xu, Huaidong Zhang, Pheng-Ann Heng: SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation https://arxiv.org/abs/2503.14097 https://arxiv.org/pdf/2503.14097 https://arxiv.org/html/2503.14097
March 19, 2025 at 6:05 AM
Weihong Chen, Xuemiao Xu, Haoxin Yang, Yi Xie, Peng Xiao, Cheng Xu, Huaidong Zhang, Pheng-Ann Heng: SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation https://arxiv.org/abs/2503.14097 https://arxiv.org/pdf/2503.14097 https://arxiv.org/html/2503.14097
Chenxi Zheng, Yihong Lin, Bangzhen Liu, Xuemiao Xu, Yongwei Nie, Shengfeng He: RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation https://arxiv.org/abs/2502.12640 https://arxiv.org/pdf/2502.12640 https://arxiv.org/html/2502.12640
February 19, 2025 at 6:10 AM
Chenxi Zheng, Yihong Lin, Bangzhen Liu, Xuemiao Xu, Yongwei Nie, Shengfeng He: RecDreamer: Consistent Text-to-3D Generation via Uniform Score Distillation https://arxiv.org/abs/2502.12640 https://arxiv.org/pdf/2502.12640 https://arxiv.org/html/2502.12640
Zikai Huang, Yihan Zhou, Xuemiao Xu, Cheng Xu, Xiaofen Xing, Jing Qin, Shengfeng He: Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation https://arxiv.org/abs/2509.02278 https://arxiv.org/pdf/2509.02278 https://arxiv.org/html/2509.02278
September 3, 2025 at 6:32 AM
Zikai Huang, Yihan Zhou, Xuemiao Xu, Cheng Xu, Xiaofen Xing, Jing Qin, Shengfeng He: Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation https://arxiv.org/abs/2509.02278 https://arxiv.org/pdf/2509.02278 https://arxiv.org/html/2509.02278
Dijia Zhan, Xuemiao Xu, Jinyi Li, Jie Tang: SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies https://arxiv.org/abs/2607.04609 https://arxiv.org/pdf/2607.04609 https://arxiv.org/html/2607.04609
July 7, 2026 at 6:45 AM
Dijia Zhan, Xuemiao Xu, Jinyi Li, Jie Tang: SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies https://arxiv.org/abs/2607.04609 https://arxiv.org/pdf/2607.04609 https://arxiv.org/html/2607.04609
Chengying Tu, Xuemiao Zhang, Rongxiang Weng, Rumei Li, Chen Zhang, Yang Bai, Hongfei Yan, Jingang Wang, Xunliang Cai
A Survey on LLM Mid-training
https://arxiv.org/abs/2510.23081
A Survey on LLM Mid-training
https://arxiv.org/abs/2510.23081
October 28, 2025 at 8:22 AM
Chengying Tu, Xuemiao Zhang, Rongxiang Weng, Rumei Li, Chen Zhang, Yang Bai, Hongfei Yan, Jingang Wang, Xunliang Cai
A Survey on LLM Mid-training
https://arxiv.org/abs/2510.23081
A Survey on LLM Mid-training
https://arxiv.org/abs/2510.23081
Xuemiao Zhang, Can Ren, Chengying Tu, Rongxiang Weng, Hongfei Yan, Jingang Wang, Xunliang Cai
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
https://arxiv.org/abs/2508.01317
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
https://arxiv.org/abs/2508.01317
August 5, 2025 at 10:40 AM
Xuemiao Zhang, Can Ren, Chengying Tu, Rongxiang Weng, Hongfei Yan, Jingang Wang, Xunliang Cai
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
https://arxiv.org/abs/2508.01317
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
https://arxiv.org/abs/2508.01317
Xuemiao Zhang, Chengying Tu, Can Ren, Rongxiang Weng, Hongfei Yan, Jingang Wang, Xunliang Cai
Large-Scale Diverse Synthesis for Mid-Training
https://arxiv.org/abs/2508.01326
Large-Scale Diverse Synthesis for Mid-Training
https://arxiv.org/abs/2508.01326
August 5, 2025 at 10:40 AM
Xuemiao Zhang, Chengying Tu, Can Ren, Rongxiang Weng, Hongfei Yan, Jingang Wang, Xunliang Cai
Large-Scale Diverse Synthesis for Mid-Training
https://arxiv.org/abs/2508.01326
Large-Scale Diverse Synthesis for Mid-Training
https://arxiv.org/abs/2508.01326
Feiyu Duan, Xuemiao Zhang, Sirui Wang, Haoran Que, Yuqi Liu, Wenge Rong, Xunliang Cai
Enhancing LLMs via High-Knowledge Data Selection
https://arxiv.org/abs/2505.14070
Enhancing LLMs via High-Knowledge Data Selection
https://arxiv.org/abs/2505.14070
May 21, 2025 at 11:54 AM
Feiyu Duan, Xuemiao Zhang, Sirui Wang, Haoran Que, Yuqi Liu, Wenge Rong, Xunliang Cai
Enhancing LLMs via High-Knowledge Data Selection
https://arxiv.org/abs/2505.14070
Enhancing LLMs via High-Knowledge Data Selection
https://arxiv.org/abs/2505.14070
Xuemiao Zhang, Feiyu Duan, Liangyu Xu, Yongwei Zhou, Sirui Wang, Rongxiang Weng, Jingang Wang, Xunliang Cai
FRAMES: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
https://arxiv.org/abs/2502.05551
FRAMES: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
https://arxiv.org/abs/2502.05551
February 11, 2025 at 12:25 PM
Xuemiao Zhang, Feiyu Duan, Liangyu Xu, Yongwei Zhou, Sirui Wang, Rongxiang Weng, Jingang Wang, Xunliang Cai
FRAMES: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
https://arxiv.org/abs/2502.05551
FRAMES: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
https://arxiv.org/abs/2502.05551