IDV Lab

2026

Wan-Alpha: Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner

Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

Haotian Dong, Wenjing Wang, Chen Li, Jing LYU, Di Lin (Corresponding Author).

PDF

Code

Project

2026

RecEdit-Drive: 3D Reconstruction-Guided Spatiotemporal Video Editing for Autonomous Driving Scenes

Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

Yipeng Wu, Xin Wang, Chenghan Yang, Chong Wang, Dongdong Wu, Wanchao Su, Hengshuang Zhao, Wei Feng, Kairui Yang, Di Lin (Corresponding Author).

PDF

Code

2026

HOPS: Hierarchical Open-vocabulary Part Segmentation with Attention-Aware Filtering and Affinity-Guided Enhancement

Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

Xinlong Li, Ruonan Liu, Shaoyiyi Gao, Yaxuan Liu, Jixian He, Jiaxin Li, Qing Guo, Kairui Yang, Wei Feng, Di Lin (Corresponding Author).

PDF

Code

2026

Multi-modal Frequency Decomposition Network for Semantic Scene Completion

Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

Die Zuo, Kairui Yang, Lubo Wang, Ruonan Liu, Qing Guo, Chong Wang, Dongdong Wu, Wei Feng, Di Lin (Corresponding Author).

PDF

Code

2026

BA-GS: Bayesian Adaptive Gaussian Splatting for SFM-Free 3D Reconstruction

Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

Zhongjie Ma, Xin Wang, Haotian Dong, Chong Wang, Dongdong Wu, Changqing Zhang, Di Lin (Corresponding Author).

PDF

Code

2026

DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning

Conference on Computer Vision and Pattern Recognition (CVPR), 2026.

Zhe Liu, Runhui Huang, Rui Yang, Siming Yan, Zining Wang, Lu Hou, Di Lin, Xiang Bai, Hengshuang Zhao.

PDF

Code

2026

OccDriver: Future Occupancy Guided Dual-branch Trajectory Planner in Autonomous Driving

International Conference on Learning Representations (ICLR), 2026.

Zhao Huang, Bowen Zhang, Zhongzhu Li, Di Lin (Corresponding Author).

PDF

Code

2026

FreeMem: Enhancing Consistency in Long Video Generation via Tuning-Free Memory

AAAI Conference on Artificial Intelligence (AAAI), 2026.

Jibin Peng, Di Lin (Co-first Author), Zhecheng Xu, Haoran Lu, Ruonan Liu, Wuyuan Xie, Miaohui Wang, Lingyu Liang, Yi Wang, Qing Guo.

PDF

Code

2026

CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving

AAAI Conference on Artificial Intelligence (AAAI), 2026.

Enhui Ma, Lijun Zhou, Tao Tang, Jiahuan Zhang, Junpeng Jiang, Zhan Zhang, Dong Han, Kun Zhan, Xueyang Zhang, Xianpeng Lang, Haiyang Sun, Xia Zhou, Di Lin, Kaicheng Yu.

PDF

Code

2026

Firing Bits Where It Matters: Spiking-Guided Just Recognizable Distortion Modeling for Machine-Centric Video Coding

AAAI Conference on Artificial Intelligence (AAAI), 2026.

Wuyuan Xie, Zhenming Li, Yuwu Lu, Di Lin, Yun Song, Miaohui Wang.

PDF

Code

2026

Exploiting Geometric Structures for Modeling Multi-Agent Behaviors: A New Thinking

AAAI Conference on Artificial Intelligence (AAAI), 2026, (Oral Presentation).

Bohao Qu, Xiaofeng Cao, Bing Li, Menglin Zhang, Tuan-Anh Vu, Di Lin, Qing Guo.

PDF

Code

2026

Causal Inference via Style Bias Deconfounding for Domain Generalization

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026.

Jiaxi Li, Di Lin, Hao Chen, Hongying Liu, Liang Wan, Wei Feng.