Cover Image

Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Strong, Matthew, Chang, Wei-Jer, Herau, Quentin, Yang, Jiezhi, Hu, Yihan, Peng, Chensheng, Zhan, Wei
Format:	Preprint
Published:	2026
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

SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
by: Herau, Quentin, et al.
Published: (2026)

UniQueR: Unified Query-based Feedforward 3D Reconstruction
by: Peng, Chensheng, et al.
Published: (2026)

Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution
by: Xu, Tianshuo, et al.
Published: (2026)

URoPE: Universal Relative Position Embedding across Geometric Spaces
by: Xie, Yichen, et al.
Published: (2026)

RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space
by: Xie, Yichen, et al.
Published: (2026)

SPACeR: Self-Play Anchoring with Centralized Reference Models
by: Chang, Wei-Jer, et al.
Published: (2025)

S2GO: Streaming Sparse Gaussian Occupancy Prediction
by: Park, Jinhyung, et al.
Published: (2025)

NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
by: Rawal, Ishaan, et al.
Published: (2026)

PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence
by: Chen, Zequn, et al.
Published: (2024)

Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
by: Barkley, Brett, et al.
Published: (2026)

Van der Waals Heterostructure Contact Strategy for Barrier‐Free 2D Complementary Transistors
by: Pengpeng Sang, et al.
Published: (2024)

Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model
by: Huang, Yaxuan, et al.
Published: (2025)

Label-Free Intraoperative Imaging of Hemodynamics using Deep Learning
by: Shi, Yan, et al.
Published: (2024)

LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation
by: Chang, Wei-Jer, et al.
Published: (2025)

SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries
by: Chang, Wei-Jer, et al.
Published: (2023)

Scaling Video Pretraining for Surgical Foundation Models
by: Lu, Sicheng, et al.
Published: (2026)

Label-Free Subjective Player Experience Modelling via Let's Play Videos
by: Goel, Dave, et al.
Published: (2024)

EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decomposition
by: Hu, Yihan, et al.
Published: (2025)

Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views
by: Bao, Chong, et al.
Published: (2025)

MindCine: Multimodal EEG-to-Video Reconstruction with Large-Scale Pretrained Models
by: Zhou, Tian-Yi, et al.
Published: (2026)

Calibration‐Free Electromyography Motor Intent Decoding Using Large‐Scale Supervised Pretraining
by: Alexander E. Olsson, et al.
Published: (2026)

On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
by: Meuleman, Andreas, et al.
Published: (2025)

GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
by: Bansal, Hritik, et al.
Published: (2024)

ScheduleFree+: Scaling Learning-Rate-Free & Schedule-Free Learning to Large Language Models
by: Defazio, Aaron
Published: (2026)

X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
by: Xie, Yichen, et al.
Published: (2024)

Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inference
by: Cheng, Wei, et al.
Published: (2024)

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
by: Peng, Chensheng, et al.
Published: (2024)

A Sensitive and Label‐Free Ratiometric Fluorescent Aptasensor for Rapid Quinine Detection in Environmental and Food Samples
by: Lingli Bu, et al.
Published: (2025)

Pose Optimization for Autonomous Driving Datasets using Neural Rendering Models
by: Herau, Quentin, et al.
Published: (2025)

LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving
by: Kong, Lingdong, et al.
Published: (2025)

Free Energy and Network Structure: Breaking Scale-Free Behaviour Through Information Processing Constraints
by: Williams, Peter R, et al.
Published: (2025)

FreeA: Human-object Interaction Detection using Free Annotation Labels
by: Liu, Qi, et al.
Published: (2024)

LLM-Inspired Pretrain-Then-Finetune for Small-Data, Large-Scale Optimization
by: Zhang, Zishi, et al.
Published: (2026)

Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the Wild
by: Bao, Peijun, et al.
Published: (2024)

BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training
by: Zhang, Xuanpu, et al.
Published: (2024)

HetroD: A High-Fidelity Drone Dataset and Benchmark for Autonomous Driving in Heterogeneous Traffic
by: Chen, Yu-Hsiang, et al.
Published: (2026)

Dimensional Regulation in Metal‐Free Perovskites by Compositional Engineering to Achieve Record Low X‐Ray Detection Limits
by: Pengxiang Dong, et al.
Published: (2024)

LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation
by: Jiang, Bo, et al.
Published: (2026)

Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors
by: Hu, Haichen, et al.
Published: (2025)

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
by: Zhang, Shengjun, et al.
Published: (2026)