Termsslug: end-to-end-learning

End-to-End Learning

端到端学习

Training a model or system as a whole from raw input to final output without hand-engineered stages.

Curated Intelligence

6 items · Page 1/1
Hacker News AIT2·Infra
58 pts
Chip That Plays Connect-4 Learned End-to-End for Under $10

The author argues that extreme hardware specialization, where a dataset is compiled directly into custom silicon, is closer than expected. As a proof point, a single-cycle Connect-4 chip was learned end-to-end from simulated games for under $10 of compute, running at ~25 MHz and consuming a few hundred picojoules per move, matching a CPU engine's speed at two to three orders of magnitude lower energy.

InfoQ 中文T2·Models
68 pts
Baidu Unveils Apollo World Model for Autonomous Driving Validation

Baidu unveiled Apollo World, a full-modal world model for physical AI, introducing '2+3' criteria that prioritize causal fidelity over visual rendering. By modeling traffic participants as decision-making agents, it provides a high-fidelity virtual training environment for Luobo Kuaipao (Apollo Go), aiming to resolve the 'impossible triangle' of safety, real-time performance, and interaction in autonomous driving to accelerate large-scale L4 deployment.

Berkeley AI Research (BAIR)T1·Models
68 pts
Information-Driven Imaging Design Method

The BAIR team proposes an information-theoretic framework for evaluating imaging systems at NeurIPS 2025, directly quantifying useful information in noisy measurements. This method replaces traditional metrics like resolution or SNR with an estimator that assesses object distinguishability from raw data, targeting AI-driven non-visual imaging scenarios such as autonomous driving and MRI. Code is open-sourced.

Hugging Face BlogT1·Open Source
78 pts
LeRobot Integrates L2D: World's Largest Open-Source Self-Driving Dataset

The Hugging Face LeRobot framework now supports L2D, the world's largest open-source multimodal self-driving dataset. Comprising over 90 TB of data from 30 German cities (5000+ hours), it includes HD camera feeds, vehicle states, and natural language instructions, specifically designed for training end-to-end autonomous driving models.