The SNG framework and SNG-VLA model enable end-to-end driving systems to better incorporate global navigation for state-of-the-art route following without auxiliary perception losses.
Drivegpt4: Interpretable end-to-end autonomous driving via large language model
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
support 1representative citing papers
RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
SteinsGateDrive decouples LLM inference latency from vehicle control by pre-selecting alpha, beta, and gamma worldline futures that a runtime validates against safety contracts until abort conditions trigger.
RIA is a closed-loop system where an LLM reasons about actions, a world model imagines outcomes via rollouts, and a safety scorer selects the best action, demonstrated in CARLA with 80.05% route completion and low collision rate.
C-CoT applies VLMs to autonomous driving via five-stage reasoning with a meta-action tree for counterfactuals, yielding 81.9% risk recall, 3.52% collision rate, and 1.98 m L2 error on a new dataset.
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.
citing papers explorer
-
Unveiling the Surprising Efficacy of Navigation Understanding in End-to-End Autonomous Driving
The SNG framework and SNG-VLA model enable end-to-end driving systems to better incorporate global navigation for state-of-the-art route following without auxiliary perception losses.
-
RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation
RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
-
Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning
SteinsGateDrive decouples LLM inference latency from vehicle control by pre-selecting alpha, beta, and gamma worldline futures that a runtime validates against safety contracts until abort conditions trigger.
-
Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving
RIA is a closed-loop system where an LLM reasons about actions, a world model imagines outcomes via rollouts, and a safety scorer selects the best action, demonstrated in CARLA with 80.05% route completion and low collision rate.
-
C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
C-CoT applies VLMs to autonomous driving via five-stage reasoning with a meta-action tree for counterfactuals, yielding 81.9% risk recall, 3.52% collision rate, and 1.98 m L2 error on a new dataset.
-
Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.