Botian Shi

13

Papers

83

Total Citations

Papers (13)

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

Docopilot: Improving Multimodal Models for Document-Level Understanding

Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching

Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning

Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection

Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection

DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection

LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion

OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations

Chimera: Improving Generalist Model with Domain-Specific Experts

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection