Xiaosong Jia

Orcid: 0000-0002-5222-1476

According to our database1, Xiaosong Jia authored at least 47 papers between 2020 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling.
CoRR, May, 2026

Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations.
CoRR, May, 2026

GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization.
CoRR, May, 2026

Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval.
CoRR, May, 2026

SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation.
CoRR, May, 2026

Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models.
CoRR, April, 2026

Can Users Specify Driving Speed? Bench2Drive-Speed: Benchmark and Baselines for Desired-Speed Conditioned Autonomous Driving.
CoRR, March, 2026

ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments.
CoRR, March, 2026

PointAlign: Feature-Level Alignment Regularization for 3D Vision-Language Models.
CoRR, March, 2026

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention.
CoRR, February, 2026

2025
Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank.
CoRR, December, 2025

Spatial Retrieval Augmented Autonomous Driving.
CoRR, December, 2025

DriveVGGT: Visual Geometry Transformer for Autonomous Driving.
CoRR, November, 2025

LaGen: Towards Autoregressive LiDAR Scene Generation.
CoRR, November, 2025

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving.
CoRR, November, 2025

PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection.
Int. J. Comput. Vis., September, 2025

TrajTok: Technical Report for 2025 Waymo Open Sim Agents Challenge.
CoRR, June, 2025

DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving.
CoRR, May, 2025

Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions.
CoRR, May, 2025

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2).
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

ReSim: Reliable World Simulation for Autonomous Driving.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

FlatFusion: Delving Into Details of Sparse Transformer-Based Camera-LiDAR Fusion for Autonomous Driving.
Proceedings of the IEEE International Conference on Robotics and Automation, 2025

Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Delving Into the Devils of Bird's-Eye-View Perception: A Review, Evaluation and Recipe.
IEEE Trans. Pattern Anal. Mach. Intell., April, 2024

Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model.
CoRR, 2024

AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving.
CoRR, 2024

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving.
CoRR, 2024

Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2).
CoRR, 2024

Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-V2).
Proceedings of the Computer Vision - ECCV 2024, 2024

2023
HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding.
IEEE Trans. Pattern Anal. Mach. Intell., November, 2023

LLM4Drive: A Survey of Large Language Models for Autonomous Driving.
CoRR, 2023

Policy Pre-training for End-to-end Autonomous Driving via Self-supervised Geometric Modeling.
CoRR, 2023

Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Planning-oriented Autonomous Driving.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Using Survival Theory in Early Pattern Detection for Viral Cascades.
IEEE Trans. Knowl. Data Eng., 2022

Goal-oriented Autonomous Driving.
CoRR, 2022

Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe.
CoRR, 2022

Learning Substructure Invariance for Out-of-Distribution Molecular Representations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Towards Capturing the Temporal Dynamics for Trajectory Prediction: a Coarse-to-Fine Approach.
Proceedings of the Conference on Robot Learning, 2022

2021
IDE-Net: Interactive Driving Event and Pattern Extraction From Human Data.
IEEE Robotics Autom. Lett., 2021

Multi-Agent Trajectory Prediction by Combining Egocentric and Allocentric Views.
Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

2020
SentiMem: Attentive Memory Networks for Sentiment Classification in User Review.
Proceedings of the Database Systems for Advanced Applications, 2020


  Loading...