Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/5ECCV 2026Poster

Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention

Bingde Liu · Wu Ran · Jinglei Zhang · Huanhuan Yuan · Chao Ma

多模态效率与系统长上下文与架构Low-Level Vision, Restoration & Generative PriorsOpenReview

作者位次 #7/7ECCV 2026Poster

Aggregating Cross-Domain Knowledge via Learnable Tokens for Multi-Teacher Distillation

Wu Ran · Weijia Zhang · ShuYang Pang · JingSheng Liu · Xiaohui Zhang · Yichao Yan · Chao Ma

安全强化学习与后训练效率与系统Federated, Continual & Efficient Learning; Model SecurityOpenReview

作者位次 #5/5ECCV 2026Poster

Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving

Guoqing Wang · Pin Tang · Xiangxuan Ren · Liping Hou · Chao Ma

3D Reconstruction, Gaussian Splatting & Neural RenderingOpenReview

作者位次 #8/13ECCV 2026Poster

OmniNWM: Unifying the State-Action-Reward Triad for Closed-Loop Panoramic Driving Navigation World Models

Bohan Li · Zhuang Ma · Dalong Du · Baorui Peng · Zhujin Liang · Zhenqiang Liu · Xianda Guo · Chao Ma · Yueming Jin · Zheng Zhu · HAO ZHAO · Wenjun Zeng · Xin Jin

Embodied AI, Robotics & Autonomous DrivingOpenReview

作者位次 #7/7ECCV 2026Poster

PixelPilot: Scalable Vision-Language-Action Models for End-to-End Autonomous Driving

Pin Tang · Guoqing Wang · Xiangxuan Ren · Zhongdao Wang · Guodongfang Zhao · Bailan Feng · Chao Ma

多模态Embodied AI, Robotics & Autonomous DrivingOpenReview

作者位次 #3/3ECCV 2026Poster

PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection

Xuanming Shang · Weijia Zhang · Chao Ma

效率与系统长上下文与架构Geometry, Localization, Matching & MotionOpenReview

作者位次 #7/7CVPR 2026Poster· Computer Vision & Pattern Recognition

Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models

Yuehao Liu · Shanyan Guan · Weijia Zhang · Xuanming Shang · Yanhao Ge · Wei Li · Chao Ma

多模态OpenReview 项目页

作者位次 #7/7CVPR 2026Oral· Computer Vision & Pattern Recognition

Guiding a Diffusion Model by Swapping Its Tokens

Weijia Zhang · Yuehao Liu · Shanyan Guan · Wu Ran · Yanhao Ge · Wei Li · Chao Ma

多模态OpenReview 项目页

作者位次 #4/7CVPR 2026Spotlight· Computer Vision & Pattern Recognition

Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems

Jiahuan Long · Tingsong Jiang · Hanqing Liu · Chao Ma · Weien Zhou · Yang Yang · Wen Yao

安全多模态OpenReview 项目页

作者位次 #12/15ICRA 2026Oral· Robotics & Automation

Unified Map Prior Encoder for Mapping and Planning

Zongzheng Zhang · Sizhe Zou · Guantian Zheng · Zhenxin Zhu · Yu Gao · Guoxuan Chi · Shuo Wang · Yuwen Heng · Zhigang Sun · Yiru Wang · Hao Sun · Chao Ma · Zhen Li · Anqing Jiang · Hao Zhao

推理OpenReview

作者位次 #4/6AAAI 2026Poster· Artificial Intelligence

Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame

Qinglong Cao · Xirui Li · Ding Wang · Chao Ma · Yuntian Chen · Xiaokang Yang

多模态检索与知识OpenReview

作者位次 #8/8AAAI 2026Poster· Artificial Intelligence

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models

Jiahuan Long · Tingsong Jiang · Wen Yao · Yizhe Xiong · Zhengqin Xu · Shuai Jia · Hanqing Liu · Chao Ma

多模态强化学习与后训练OpenReview

Chao Ma

获取完整研究档案

联系方式