朝花夕拾

不讲条件，不找借口，坚定信念，完美执行！

置顶

Climbing

Coding

Deep Learning

Optimization

Reforce. Learning

Reforce. Learning

Robotics

Tools

Robotics

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation

Climbing

野攀岩场记录

Robotics

ReflectDrive-2 论文阅读笔记

Climbing

攀岩户外技能

Robotics

X-Cache

Robotics

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

Robotics

MOSAIC: 基于规模感知的自动驾驶数据挑选魔法阵

Robotics

DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

Robotics

SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving

Robotics

Fast-WAM - 世界动作模型在推理时真的需要"脑补"未来吗？