Researcher — paper.dinq.me

2026 顶会论文

作者位次 #9/9ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Pengxiang Li · Yinan Zheng · Yue Wang · Huimin Wang · Hang Zhao · Jingjing Liu · Xianyuan Zhan · Kun Zhan · XianPeng Lang

多模态OpenReview

作者位次 #6/7ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking

Weicheng Zheng · Xiaofei Mao · Nanfei Ye · Pengxiang Li · Kun Zhan · XianPeng Lang · Hang Zhao

多模态OpenReview

作者位次 #7/9CVPR 2026Poster· Computer Vision & Pattern Recognition

SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving

Jingyu Li · Junjie Wu · Dongnan Hu · Xiangkai Huang · Bin Sun · Zhihui Hao · XianPeng Lang · Xiatian Zhu · Li Zhang

多模态OpenReview 项目页

作者位次 #7/8CVPR 2026Poster· Computer Vision & Pattern Recognition

CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Driving

Pei Liu · Qingtian Ning · Xinyan Lu · Haipeng LIU · Weiliang Ma · Dangen She · XianPeng Lang · Jun Ma

推理多模态OpenReview 项目页

作者位次 #10/12CVPR 2026Poster· Computer Vision & Pattern Recognition

PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning

Hongchen Li · Tianyu Li · Jiazhi Yang · Mingyang Shang · Gaoqiang Wu · Caojun Wang · Haochen Tian · Zengrong Lin · Zhihui Hao · XianPeng Lang · Jia Hu · Hongyang Li

多模态强化学习与后训练效率与系统OpenReview 项目页

作者位次 #12/13CVPR 2026Poster· Computer Vision & Pattern Recognition

DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving

Enhui Ma · Jiahuan Zhang · Guantian Zheng · Tao Tang · Shengbo Eben Li · Yuhang Lu · Xia Zhou · Xueyang Zhang · Yifei Zhan · Kun Zhan · Zhihui Hao · XianPeng Lang · Kaicheng Yu

推理多模态评测与基准OpenReview 项目页

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

Unifying Language-Action Understanding and Generation for Autonomous Driving

Xinyang Wang · Qian Liu · Wenjie Ding · Zhao Yang · Wei Li · Chang Liu · Bailin Li · Kun Zhan · XianPeng Lang · Wei Chen

多模态OpenReview 项目页

作者位次 #13/13ICRA 2026Oral· Robotics & Automation

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

Mengxiang Hao · Xin Jiang · Xinghao Huang · Wenliang Su · Zhiteng Wang · Junjie Rao · Xiaotian Yang · Wei Liao · Chengyu Han · Gen Liang · Yulun Song · Zhitao Xu · XianPeng Lang

OpenReview

作者位次 #10/10ICRA 2026Oral· Robotics & Automation

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning

Titong Jiang · Xuefeng Jiang · Yuan Ma · Xin Wen · Bailin Li · Kun Zhan · Peng Jia · Yahui Liu · Sheng Sun · XianPeng Lang

效率与系统多模态OpenReview

作者位次 #12/14ICRA 2026Oral· Robotics & Automation

Data Scaling Laws for Imitation Learning-Based End-to-End Autonomous Driving

Yupeng Zheng · Pengxuan Yang · Zhongpu Xia · Qichao Zhang · Yuhang Zheng · Bu Jin · Teng Zhang · Ben Lu · Chao Han · Weize Li · Songen Gu · XianPeng Lang · Xiangyuan Lan · Dongbin Zhao

数据与预训练OpenReview

作者位次 #9/10ICRA 2026Oral· Robotics & Automation

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving

Xuefeng Jiang · Yuan Ma · Pengxiang Li · Leimeng Xu · Xin Wen · Kun Zhan · Zhongpu Xia · Peng Jia · XianPeng Lang · Sheng Sun

可解释性多模态OpenReview

作者位次 #10/10AAAI 2026Poster· Artificial Intelligence

DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving

Kaiwen Cai · Xinze Liu · Xia Zhou · Hengtong Hu · Jie Xiang · Luyao Zhang · Xueyang Zhang · Kun Zhan · Yifei Zhan · XianPeng Lang

OpenReview

作者位次 #10/14AAAI 2026Poster· Artificial Intelligence

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

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

推理智能体与工具OpenReview

作者位次 #8/10AAAI 2026Poster· Artificial Intelligence

WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

Pengxuan Yang · Ben Lu · Zhongpu Xia · Chao Han · Yinfeng Gao · Teng Zhang · Kun Zhan · XianPeng Lang · Yupeng Zheng · Qichao Zhang

强化学习与后训练推理OpenReview

作者位次 #9/9AAAI 2026Poster· Artificial Intelligence

Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space

Jian Zhu · Zhengyu Jia · Tian Gao · Jiaxin Deng · Shidi Li · Lang Zhang · Fu Liu · Peng Jia · XianPeng Lang

多模态OpenReview

XianPeng Lang

获取完整研究档案

联系方式

2026 顶会论文

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking

SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving

CogDriver: Integrating Cognitive Inertia for Temporally Coherent Planning in Autonomous Driving

PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning

DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving

Unifying Language-Action Understanding and Generation for Autonomous Driving

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning

Data Scaling Laws for Imitation Learning-Based End-to-End Autonomous Driving

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving

DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving

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

WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving

Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space

常见合作者