SafePLUG: Empowering Multimodal LLMs with Pixel-Level Insight and Temporal Grounding for Traffic Accident Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sheng, Zihao, Huang, Zilin, Qu, Yansong, Chen, Jiancong, Luo, Yuhao, Chen, Yen-Jung, Leng, Yue, Chen, Sikai
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving
by: Qu, Yansong, et al.
Published: (2025)

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models
by: Sheng, Zihao, et al.
Published: (2025)

VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving
by: Huang, Zilin, et al.
Published: (2024)

Found-RL: foundation model-enhanced reinforcement learning for autonomous driving
by: Qu, Yansong, et al.
Published: (2026)

Trustworthy Human-AI Collaboration: Reinforcement Learning with Human Feedback and Physics Knowledge for Safe Autonomous Driving
by: Huang, Zilin, et al.
Published: (2024)

Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control
by: Sheng, Zihao, et al.
Published: (2024)

Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future Transportation
by: Huang, Zilin, et al.
Published: (2025)

DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving
by: Huang, Zilin, et al.
Published: (2026)

MetaSSC: Enhancing 3D Semantic Scene Completion for Autonomous Driving through Meta-Learning and Long-sequence Modeling
by: Qu, Yansong, et al.
Published: (2024)

HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving
by: Huang, Zilin, et al.
Published: (2024)

Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving
by: Huang, Zilin, et al.
Published: (2026)

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
by: Deng, Andong, et al.
Published: (2024)

mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
by: Ye, Qinghao, et al.
Published: (2023)

Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA
by: Benmahane, Yahya, et al.
Published: (2025)

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
by: Zhang, Tao, et al.
Published: (2025)

An Attack Traffic Identification Method Based on Temporal Spectrum
by: Xie, Wenwei, et al.
Published: (2024)

Abductive Ego-View Accident Video Understanding for Safe Driving Perception
by: Fang, Jianwu, et al.
Published: (2024)

ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
by: Sheng, Zihao, et al.
Published: (2026)

CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
by: Gan, Rui, et al.
Published: (2026)

Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
by: Kang, Minseok, et al.
Published: (2025)

Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction
by: Gao, Xiaowei, et al.
Published: (2023)

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
by: Hu, Anwen, et al.
Published: (2024)

Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems
by: Zou, Xingchen, et al.
Published: (2025)

ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice
by: Hu, Yutong, et al.
Published: (2024)

ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset
by: Chen, Zihao, et al.
Published: (2025)

A Physics Enhanced Residual Learning (PERL) Framework for Vehicle Trajectory Prediction
by: Long, Keke, et al.
Published: (2023)

A Modular PLUG-IN Photosynthetic Chassis With Tunable Thermal Control for Mammalian Systems.
by: Gan, Qinhua, et al.
Published: (2026)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
by: Wang, Nan, et al.
Published: (2026)

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
by: Tang, Yolo Yunlong, et al.
Published: (2024)

Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding
by: Lohner, Aaron, et al.
Published: (2024)

Multi-Stage VLM Pipeline for Zero-Shot Traffic Accident Understanding
by: Tatematsu, Fumiya, et al.
Published: (2026)

Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding
by: Yang, Zaiquan, et al.
Published: (2025)

Accident Anticipation via Temporal Occurrence Prediction
by: Zhao, Tianhao, et al.
Published: (2025)

Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis
by: Li, Lei-lei, et al.
Published: (2025)

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation
by: Athar, Ali, et al.
Published: (2024)

Urban Traffic Accident Risk Prediction Revisited: Regionality, Proximity, Similarity and Sparsity
by: Chen, Minxiao, et al.
Published: (2024)

Reconstruction of the Motion of Traffic Accident Vehicle in the Vehicle‐Mounted Video Based on Direct Linear Transform
by: Hao Feng, et al.
Published: (2024)

Multisource Accident Datasets‐Driven Deep Learning‐Based Traffic Accident Portrait for Accident Reasoning
by: Chun-Hao Wang, et al.
Published: (2024)

How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms
by: Jin, Shengji, et al.
Published: (2026)

Optimizing Antenna Coding for Pixel Antenna Empowered SISO-OFDM Systems
by: Qiao, Tianrui, et al.
Published: (2026)