Pengfei Li

Orcid: 0009-0009-8114-6207

Affiliations:
  • Tsinghua University, Institute for AI Industry Research (AIR), Beijing, China


According to our database1, Pengfei Li authored at least 25 papers between 2021 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model.
CoRR, July, 2025

Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation.
CoRR, March, 2025

Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
P-MapNet: Far-Seeing Map Generator Enhanced by Both SDMap and HDMap Priors.
IEEE Robotics Autom. Lett., October, 2024

GaussianGrasper: 3D Language Gaussian Splatting for Open-Vocabulary Robotic Grasping.
IEEE Robotics Autom. Lett., September, 2024

City-scale continual neural semantic mapping with three-layer sampling and panoptic representation.
Knowl. Based Syst., 2024

PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning.
CoRR, 2024

MonoOcc: Digging into Monocular Semantic Occupancy Prediction.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes.
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
Learning Point-wise Abstaining Penalty for Point Cloud Anomaly Detection.
CoRR, 2023

LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Unsupervised Road Anomaly Detection with Language Anchors.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

ADAPT: Action-aware Driving Caption Transformer.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds.
Proceedings of the IEEE International Conference on Robotics and Automation, 2023

3D Implicit Transporter for Temporally Consistent Keypoint Discovery.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

INT2: Interactive Trajectory Prediction at Intersections.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Long-Term Interactive Driving Simulation: MPC to the Rescue.
Proceedings of the Artificial Intelligence - Third CAAI International Conference, 2023

M<sup>2</sup>Sim: A Long-Term Interactive Driving Simulator.
Proceedings of the Artificial Intelligence - Third CAAI International Conference, 2023

2022
City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation.
CoRR, 2022

TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021
Semi-supervised Implicit Scene Completion from Sparse LiDAR.
CoRR, 2021


  Loading...