Researcher — paper.dinq.me

2026 顶会论文

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

Breaking Manifold Continuity: Vector Quantized Modeling for Real-Centric Deepfake Detection

Changshuo Wang · Jiangming Wang · Ke-Yue Zhang · Taiping Yao · Shouhong Ding · Ran Yi · Lizhuang Ma

多模态效率与系统OpenReview

作者位次 #5/7ICML 2026Poster· Applications / Computer Vision

S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction

Renhe Zhang · Yuyang Tan · Jingyu Gong · Zhizhong Zhang · Lizhuang Ma · Yuan Xie · Xin Tan

多模态OpenReview

作者位次 #8/9ICML 2026Poster

More Sail than Ballast: Addressing Harmful Knowledge Leakage in the Expansive Reasoning Space of LRMs

Qibing Ren · Xinhao Song · Ke Fan · Lijun Li · Zhanpeng Zhou · Gongshen Liu · Junchi Yan · Lizhuang Ma · Jing Shao

推理安全检索与知识OpenReview

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

Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration

Sen Wang · Bangwei Liu · Zhenkun Gao · Lizhuang Ma · Xuhong Wang · Yuan Xie · Xin Tan

多模态强化学习与后训练评测与基准OpenReview 项目页

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

S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs

Yuzhou Ji · Qijian Tian · He Zhu · Xiaoqi Jiang · Guangzhi Cao · Lizhuang Ma · Yuan Xie · Xin Tan

多模态OpenReview 项目页

作者位次 #9/9CVPR 2026Poster· Computer Vision & Pattern Recognition

Open the Motion Door: Atomic Motion Decomposition and Recomposition for Open-Vocabulary Motion Generation

Ke Fan · Jiangning Zhang · Ran Yi · Jingyu Gong · Yabiao Wang · Yating Wang · Xin Tan · Chengjie Wang · Lizhuang Ma

多模态OpenReview 项目页

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

PoseAnything: General Pose-guided Video Generation with Part-aware Temporal Coherence

Ruiyan Wang · Teng Hu · Kaihui Huang · Zihan Su · Ran Yi · Lizhuang Ma

多模态OpenReview 项目页

作者位次 #9/10CVPR 2026Poster· Computer Vision & Pattern Recognition

Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning

Zhenwu Shi · Jingyu Gong · Peiwei Wang · Xingzan Wang · Tianwen Qian · Wenxi Li · Yuan Fang · Jiao Xie · Lizhuang Ma · Shaohui Lin

多模态OpenReview 项目页

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

Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection

Changshuo Wang · Jiangming Wang · Ke-Yue Zhang · Taiping Yao · Shouhong Ding · Shunli Wang · Ran Yi · Lizhuang Ma

多模态理论与学习动力学OpenReview 项目页

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

Multi-Step Deformable Gaussian Splatting for Dynamic Scene Rendering

Jiaheng Hu · Zhizhong Zhang · Jingyu Gong · Lizhuang Ma · Xin Tan · Yuan Xie

OpenReview

作者位次 #5/6AAAI 2026Poster· Artificial Intelligence

LidarPainter: One-Step Away from Any Lidar View to Novel Guidance

Yuzhou Ji · Ke Ma · Hong Cai · Anchun Zhang · Lizhuang Ma · Xin Tan

OpenReview

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

TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis

Yiwen Wang · Ran Yi · Lizhuang Ma

OpenReview

作者位次 #6/7AAAI 2026Poster· Artificial Intelligence

PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification

Hao Yang · Qianyu Zhou · Haijia Sun · Xiangtai Li · Xuequan Lu · Lizhuang Ma · Shuicheng YAN

理论与学习动力学长上下文与架构OpenReview

Lizhuang Ma

获取完整研究档案

联系方式

2026 顶会论文

Breaking Manifold Continuity: Vector Quantized Modeling for Real-Centric Deepfake Detection

S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction

More Sail than Ballast: Addressing Harmful Knowledge Leakage in the Expansive Reasoning Space of LRMs

Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration

S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs

Open the Motion Door: Atomic Motion Decomposition and Recomposition for Open-Vocabulary Motion Generation

PoseAnything: General Pose-guided Video Generation with Part-aware Temporal Coherence

Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning

Beyond [CLS] Token: Query-Driven Token-Level Forgery Purification for Generalizable Deepfake Detection

Multi-Step Deformable Gaussian Splatting for Dynamic Scene Rendering

LidarPainter: One-Step Away from Any Lidar View to Novel Guidance

TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis

PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification

常见合作者