VLA-World improves autonomous driving by using action-guided future image generation followed by reflective reasoning over the imagined scene to refine trajectories.
hub Canonical reference
Drivegpt4: Interpretable end-to-end autonomous driving via large language model
Canonical reference. 83% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
83% of classified citations
hub tools
citation-role summary
background 5
dataset 1
citation-polarity summary
representative citing papers
AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.
The paper fine-tunes Qwen3.5-4B as a driving VLA using serialized decision traces from rule-based planners, reporting reduced ADE and miss rate on a simulator benchmark with camera inputs.
EgoDyn-Bench finds a Perception Bottleneck: foundation models hold ego-motion logic in language but misalign it with vision, underperforming geometric baselines until given explicit trajectories.
LMGenDrive unifies LLM-based multimodal understanding with generative world models to output both future driving videos and control signals for end-to-end closed-loop autonomous driving.
SAVANT reformulates semantic anomaly detection as layered consistency verification, raising VLM recall by 18.5% on real driving images and enabling a fine-tuned 7B open model to reach 90.8% recall and 93.8% accuracy.
Senna decouples language-based high-level planning from an LVLM with low-level trajectory prediction from an E2E model, reporting 27% lower planning error and 33% lower collisions after pre-training on DriveX and fine-tuning on nuScenes.
VADv2 introduces a probabilistic planning model that discretizes the high-dimensional action space into tokens, interacts them with scene tokens to predict action distributions, and reports SOTA closed-loop results on CARLA Town05 and Bench2Drive.
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
SARAD is a hybrid LLM-DRL framework for autonomous driving that replaces random exploration with RAG-enhanced LLM guidance, an attention discriminator, and a collision predictor, reporting performance gains in the Highway-Env simulator.
AtteConDA adds attention-based conflict suppression to multi-condition diffusion models so that generated driving-scene images retain richer structural cues from the original annotations.
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
citing papers explorer
-
Learning Vision-Language-Action World Models for Autonomous Driving
VLA-World improves autonomous driving by using action-guided future image generation followed by reflective reasoning over the imagined scene to refine trajectories.
-
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.
-
Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs
The paper fine-tunes Qwen3.5-4B as a driving VLA using serialized decision traces from rule-based planners, reporting reduced ADE and miss rate on a simulator benchmark with camera inputs.
-
EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
EgoDyn-Bench finds a Perception Bottleneck: foundation models hold ego-motion logic in language but misalign it with vision, underperforming geometric baselines until given explicit trajectories.
-
LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving
LMGenDrive unifies LLM-based multimodal understanding with generative world models to output both future driving videos and control signals for end-to-end closed-loop autonomous driving.
-
Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning
SAVANT reformulates semantic anomaly detection as layered consistency verification, raising VLM recall by 18.5% on real driving images and enabling a fine-tuned 7B open model to reach 90.8% recall and 93.8% accuracy.
-
Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
Senna decouples language-based high-level planning from an LVLM with low-level trajectory prediction from an E2E model, reporting 27% lower planning error and 33% lower collisions after pre-training on DriveX and fine-tuning on nuScenes.
-
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
VADv2 introduces a probabilistic planning model that discretizes the high-dimensional action space into tokens, interacts them with scene tokens to predict action distributions, and reports SOTA closed-loop results on CARLA Town05 and Bench2Drive.
-
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
-
SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous Driving
SARAD is a hybrid LLM-DRL framework for autonomous driving that replaces random exploration with RAG-enhanced LLM guidance, an attention discriminator, and a collision predictor, reporting performance gains in the Highway-Env simulator.
-
AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation
AtteConDA adds attention-based conflict suppression to multi-condition diffusion models so that generated driving-scene images retain richer structural cues from the original annotations.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.