Cover Image

Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Yunsheng, Abdelraouf, Amr, Gupta, Rohit, Wang, Ziran, Han, Kyungtae
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PDB-Eval: An Evaluation of Large Multimodal Models for Description and Explanation of Personalized Driving Behavior
by: Wu, Junda, et al.
Published: (2025)

NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models
by: Park, Sung-Yeon, et al.
Published: (2025)

ViT-DD: Multi-Task Vision Transformer for Semi-Supervised Driver Distraction Detection
by: Ma, Yunsheng, et al.
Published: (2022)

PDB: Not All Drivers Are the Same -- A Personalized Dataset for Understanding Driving Behavior
by: Wei, Chuheng, et al.
Published: (2025)

ALN-P3: Unified Language Alignment for Perception, Prediction, and Planning in Autonomous Driving
by: Ma, Yunsheng, et al.
Published: (2025)

SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting
by: Park, Sung-Yeon, et al.
Published: (2025)

SparseDiT: Token Sparsification for Efficient Diffusion Transformer
by: Chang, Shuning, et al.
Published: (2024)

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)

Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion
by: Zhang, Jiaru, et al.
Published: (2026)

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
by: Zhang, Yuan, et al.
Published: (2024)

Scene-Aware Conversational ADAS with Generative AI for Real-Time Driver Assistance
by: Han, Kyungtae, et al.
Published: (2025)

Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection
by: Yang, Nan, et al.
Published: (2025)

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
by: Dorovatas, Vaggelis, et al.
Published: (2025)

Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture
by: Lu, Juanwu, et al.
Published: (2024)

VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification
by: Zhuang, Xianwei, et al.
Published: (2025)

Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving
by: Zhou, Hao, et al.
Published: (2024)

LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs
by: Ma, Yunsheng, et al.
Published: (2023)

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
by: Ma, Junpeng, et al.
Published: (2025)

USV: Unified Sparsification for Accelerating Video Diffusion Models
by: Wu, Xinjian, et al.
Published: (2025)

OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving
by: Tang, Tao, et al.
Published: (2025)

ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification
by: He, Yefei, et al.
Published: (2024)

AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving
by: Sekkat, Ahmed Rida, et al.
Published: (2023)

MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
by: Ataallah, Kirolos, et al.
Published: (2024)

MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving
by: Zhang, Enming, et al.
Published: (2024)

Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?
by: Bai, Yifan, et al.
Published: (2024)

TinyDrive: Multiscale Visual Question Answering with Selective Token Routing for Autonomous Driving
by: Hassani, Hossein, et al.
Published: (2025)

UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
by: Zhao, Guosheng, et al.
Published: (2026)

FAR-Drive: Frame-AutoRegressive Video Generation in Closed-Loop Autonomous Driving
by: Li, Yaoru, et al.
Published: (2026)

Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving
by: Wen, Yuqing, et al.
Published: (2024)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
by: Song, Baiyang, et al.
Published: (2026)

CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting
by: Liao, Haicheng, et al.
Published: (2025)

Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation
by: Ma, Enhui, et al.
Published: (2024)

MTA: Multimodal Task Alignment for BEV Perception and Captioning
by: Ma, Yunsheng, et al.
Published: (2024)

Instruction Tuning-free Visual Token Complement for Multimodal LLMs
by: Wang, Dongsheng, et al.
Published: (2024)

Diffusion-FS: Multimodal Free-Space Prediction via Diffusion for Autonomous Driving
by: Gupta, Keshav, et al.
Published: (2025)

VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
by: Zhu, Jiaying, et al.
Published: (2025)

RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation
by: Yan, Tianyi, et al.
Published: (2025)

Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs
by: Lu, Jinda, et al.
Published: (2026)

ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Driving
by: Cui, Can, et al.
Published: (2025)

Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving
by: Cao, Junyi, et al.
Published: (2024)