Signals 4 · free daily AI digest

DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving

Paper recorded by Signals 4 on 2026-09-22 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-22 on arXiv · recorded by Signals 4 on 2026-09-23

Category: cs.CV · 计算机视觉 · first seen 2026-09-23

Abstract

Faithfully evaluating end-to-end driving policies in simulation requires observations that are not merely photo-realistic, but preserve the scene features a policy relies on to make decisions. Existing platforms, however, exhibit a sim-to-real visual gap that corrupts policy perception, undermining their ability to assess a policy's closed-loop decision-making. To this end, we propose DreamStream,

Read on arXiv →

#18 most recent of 301 cs.CV papers we have recorded · ↑ newer: HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene S · ↓ older: StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer T
Cite this page: DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving: the #18 most recent of 301 cs.CV papers we have recorded (as of 2026-09-22). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/dreamstream-towards-policy-oriented-generative-simulation-for-end-to-end-driving.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions