Cover Image

Compressing Multi-Task Model for Autonomous Driving via Pruning and Knowledge Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiayuan, Wu, Q. M. Jonathan, Zhang, Ning, Suto, Katsuya, Zhong, Lei
Format:	Preprint
Published:	2025
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

RMT-PPAD: Real-time Multi-task Learning for Panoptic Perception in Autonomous Driving
by: Wang, Jiayuan, et al.
Published: (2025)

You Only Look at Once for Real-time and Generic Multi-Task
by: Wang, Jiayuan, et al.
Published: (2023)

A Survey on Deep Multi-Task Learning in Connected Autonomous Vehicles
by: Wang, Jiayuan, et al.
Published: (2025)

Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression
by: Schmitt, Jonas, et al.
Published: (2024)

DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model
by: Yu, Rui, et al.
Published: (2025)

Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving
by: Lian, Weitong, et al.
Published: (2026)

Distilling Multi-modal Large Language Models for Autonomous Driving
by: Hegde, Deepti, et al.
Published: (2025)

LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models
by: Zhang, Dingkun, et al.
Published: (2024)

Lightweight Model Pre-training via Language Guided Knowledge Distillation
by: Li, Mingsheng, et al.
Published: (2024)

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
by: Chen, Dong, et al.
Published: (2024)

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
by: Xiong, Minhao, et al.
Published: (2025)

Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings
by: Grashei, Christian, et al.
Published: (2025)

ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
by: Sha, Lin, et al.
Published: (2026)

Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models Compression
by: Zhang, Yongheng, et al.
Published: (2025)

Distilling the Knowledge in Data Pruning
by: Ben-Baruch, Emanuel, et al.
Published: (2024)

DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving
by: Su, Haisheng, et al.
Published: (2026)

RealDriveSim: A Realistic Multi-Modal Multi-Task Synthetic Dataset for Autonomous Driving
by: Jadon, Arpit, et al.
Published: (2025)

TwinLiteNet+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving
by: Che, Quang-Huy, et al.
Published: (2024)

Efficient Visual Question Answering Pipeline for Autonomous Driving via Scene Region Compression
by: Cai, Yuliang, et al.
Published: (2026)

DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving
by: Diao, Muxi, et al.
Published: (2025)

MoKD: Multi-Task Optimization for Knowledge Distillation
by: Hayder, Zeeshan, et al.
Published: (2025)

TT-MPD: Test Time Model Pruning and Distillation
by: Wu, Haihang, et al.
Published: (2024)

Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation
by: Lv, Chonghua, et al.
Published: (2026)

DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving
by: Shi, Chen, et al.
Published: (2025)

Decoupled Functional Evaluation of Autonomous Driving Models via Feature Map Quality Scoring
by: Zhang, Ludan, et al.
Published: (2025)

Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving
by: Zhao, Zongchuang, et al.
Published: (2025)

Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning
by: Kim, Seonghak, et al.
Published: (2023)

Image-to-Lidar Relational Distillation for Autonomous Driving Data
by: Mahmoud, Anas, et al.
Published: (2024)

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving
by: Feng, Kaituo, et al.
Published: (2024)

A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving
by: Li, Jialin, et al.
Published: (2025)

TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge
by: Zhang, Shu-Hao, et al.
Published: (2025)

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
by: Sun, Wenchao, et al.
Published: (2024)

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
by: Hu, Xiaotao, et al.
Published: (2024)

Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillation
by: Alim, Md. Samiul, et al.
Published: (2025)

Towards Universal & Efficient Model Compression via Exponential Torque Pruning
by: Modi, Sarthak Ketanbhai, et al.
Published: (2025)

ETC: Extreme Token Compression via Task-aware Visual Information Distillation in VLMs
by: Gao, Yiling, et al.
Published: (2026)

Efficient Learned Image Compression Through Knowledge Distillation
by: Allemand, Fabien, et al.
Published: (2025)

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
by: Zhang, Lingjun, et al.
Published: (2026)

Collaborative Multi-Mode Pruning for Vision-Language Models
by: Wu, Zimeng, et al.
Published: (2026)

3D Annotation-Free Learning by Distilling 2D Open-Vocabulary Segmentation Models for Autonomous Driving
by: Sun, Boyi, et al.
Published: (2024)