Papers › CarLLaVA: Vision language models for camera-only closed-loop driving

CarLLaVA: Vision language models for camera-only closed-loop driving

14 Jun 2024arXiv:2406.10165archive 2025-07-28

Katrin Renz, Long Chen, Ana-Maria Marcu, Jan Hünermann, Benoit Hanotte, Alice Karnsund, Jamie Shotton, Elahe Arani, Oleg Sinavski

In this technical report, we present CarLLaVA, a Vision Language Model (VLM) for autonomous driving, developed for the CARLA Autonomous Driving Challenge 2.0. CarLLaVA uses the vision encoder of the LLaVA VLM and the LLaMA architecture as backbone, achieving state-of-the-art closed-loop driving performance with only camera input and without the need for complex or expensive labels. Additionally, we show preliminary results on predicting language commentary alongside the driving output. CarLLaVA uses a semi-disentangled output representation of both path predictions and waypoints, getting the advantages of the path for better lateral control and the waypoints for better longitudinal control. We propose an efficient training recipe to train on large driving datasets without wasting compute on easy, trivial data. CarLLaVA ranks 1st place in the sensor track of the CARLA Autonomous Driving Challenge 2.0 outperforming the previous state of the art by 458% and the best concurrent submission by 32.6%.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

RenzKa/simlingo Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment (arXiv:2503.09594; that paper's own run record: 11 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous DrivingBench2DriveCARLA Leaderboard 2.0Language ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Bench2Drive Bench2Drive SimLingo-Base (CarLLaVa) Driving Score 85.94 #3 of 35 Archive leaderboard report
CARLA Leaderboard 2.0 CARLA CarLLaVA Driving Score 6.87 #1 of 4 Archive leaderboard report
CARLA Leaderboard 2.0 CARLA CarLLaVA Infraction Score 0.42 #1 of 4 Archive leaderboard report
CARLA Leaderboard 2.0 CARLA CarLLaVA Route Completion 18.08 #1 of 4 Archive leaderboard report
CARLA Leaderboard 2.0 CARLA CarLLaVA (Map Track) Driving Score 6.25 #2 of 4 Archive leaderboard report
CARLA Leaderboard 2.0 CARLA CarLLaVA (Map Track) Infraction Score 0.39 #2 of 4 Archive leaderboard report
CARLA Leaderboard 2.0 CARLA CarLLaVA (Map Track) Route Completion 18.89 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CARLAEntropy RegularizationLLaMAPPO

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections