Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/9ICML 2026Poster· Applications / Computer Vision

GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

Xingyilang Yin · Qi Zhang · Jiahao Chang · Ying Feng · Qingnan Fan · Xi Yang · Chi-Man Pun · Huaqi Zhang · Xiaodong Cun

多模态OpenReview

作者位次 #5/5ICML 2026Poster· Applications / Computer Vision

Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose Estimation

Zhenhua TANG · Jihua Peng · Yanbin Hao · Qiguang Miao · Chi-Man Pun

多模态OpenReview

作者位次 #4/5ICML 2026Poster· Applications / Computer Vision

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

Xingyilang Yin · Chengzhengxu Li · Jiahao Chang · Chi-Man Pun · Xiaodong Cun

多模态OpenReview

作者位次 #6/8CVPR 2026Poster· Computer Vision & Pattern Recognition

Intrinsic Concept Extraction Based on Compositional Interpretability

Hanyu Shi · Hong Tao · Guoheng Huang · Jianbin Jiang · Xuhang Chen · Chi-Man Pun · Shanhu Wang · Pan Pan

可解释性多模态长上下文与架构OpenReview 项目页

作者位次 #2/5CVPR 2026Poster· Computer Vision & Pattern Recognition

PersonaLive! Expressive Portrait Image Animation for Live Streaming

Zhiyuan Li · Chi-Man Pun · Chen Fang · Jue Wang · Xiaodong Cun

多模态理论与学习动力学OpenReview 项目页

作者位次 #2/3CVPR 2026Poster· Computer Vision & Pattern Recognition

RevINN: An End-to-End Invertible Neural Network for Reversible Adversarial Examples Generation

Jielun Huang · Chi-Man Pun · Guoheng Huang

安全多模态OpenReview 项目页

作者位次 #5/6ICRA 2026Oral· Robotics & Automation

RGA-Net: A Vision Enhancement Framework for Robotic Surgical Systems Using Reciprocal Attention Mechanisms

Quanjun Li · Weixuan Li · Han Xia · Junhua Zhou · Chi-Man Pun · Xuhang Chen

可解释性多模态OpenReview

作者位次 #7/7AAAI 2026Poster· Artificial Intelligence

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection

Jiajie Zhu · Xia Du · Xiaoyuan Liu · Ji-Zhe Zhou · Qizhen Xu · Zheng Lin · Chi-Man Pun

安全多模态OpenReview

作者位次 #3/3AAAI 2026Poster· Artificial Intelligence

OTI: A Model-free and Visually Interpretable Measure of Image Attackability

Jiaming Liang · Haowei Liu · Chi-Man Pun

多模态安全可解释性OpenReview

作者位次 #6/6AAAI 2026Poster· Artificial Intelligence

SNS-Grasp: Semantic-guided Noise Scaling for Grasp Generation

Zhenhua TANG · Yudian Zheng · Yuzhang Zhong · Haolun Li · Yanbin Hao · Chi-Man Pun

OpenReview

作者位次 #3/6CCS 2026Oral· Computer & Communications Security

Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization

Zhaoxiong Ni · Yatie Xiao · Chi-Man Pun · Fei Peng · Qingxiao Guan · Keke Tang

安全多模态OpenReview

Chi-Man Pun

获取完整研究档案

联系方式

2026 顶会论文

GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

Glimpse: Geometry Learning of Multi-scale Structural Priors for 3D Pose Estimation

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

Intrinsic Concept Extraction Based on Compositional Interpretability

PersonaLive! Expressive Portrait Image Animation for Live Streaming

RevINN: An End-to-End Invertible Neural Network for Reversible Adversarial Examples Generation

RGA-Net: A Vision Enhancement Framework for Robotic Surgical Systems Using Reciprocal Attention Mechanisms

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection

OTI: A Model-free and Visually Interpretable Measure of Image Attackability

SNS-Grasp: Semantic-guided Noise Scaling for Grasp Generation

Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt Optimization

常见合作者