ReCogDrive unifies VLM scene understanding with a diffusion planner reinforced by DiffGRPO to reach state-of-the-art results on NAVSIM and Bench2Drive benchmarks.
Finetuning generative trajectory model with reinforcement learning from human feedback
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
UniTeD unifies perception and planning in autonomous driving via shared temporal diffusion with TTM and ARS modules, reporting SOTA results on benchmarks.
BLUE trains a lightweight gate on frozen VLA hidden states to selectively activate language generation only when beneficial, achieving SOTA results with 2.54x inference speedup on driving benchmarks.
TOAD applies test-time Cross-Entropy Method optimization to refine trajectories using the planner's scorer as a reward function, improving end-to-end autonomous driving performance without retraining.
MAPLE proposes latent multi-agent rollouts with supervised fine-tuning followed by reinforcement learning using safety, progress, interaction, and diversity rewards to enable scalable closed-loop training for end-to-end autonomous driving.
SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning robustness and generalization on real benchmarks, with gains scaling by simulation
AutoVLA unifies semantic reasoning and trajectory planning in one autoregressive VLA model for end-to-end autonomous driving by tokenizing trajectories into discrete actions and using GRPO reinforcement fine-tuning to adaptively reduce unnecessary reasoning.
CaAD adds ego-centric joint-causal modeling and causality-aware policy alignment to end-to-end driving, reporting Driving Score 87.53 and PDMS 91.1 on Bench2Drive and NAVSIM.
SpanVLA reduces action generation latency via flow-matching conditioned on history and improves robustness by training on negative-recovery samples with GRPO and a dedicated reasoning dataset.
DeepSight uses parallel latent feature prediction in BEV for long-horizon world modeling and adaptive text reasoning to reach state-of-the-art closed-loop performance on the Bench2drive benchmark.
citing papers explorer
-
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
ReCogDrive unifies VLM scene understanding with a diffusion planner reinforced by DiffGRPO to reach state-of-the-art results on NAVSIM and Bench2Drive benchmarks.
-
UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving
UniTeD unifies perception and planning in autonomous driving via shared temporal diffusion with TTM and ARS modules, reporting SOTA results on benchmarks.
-
BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving
BLUE trains a lightweight gate on frozen VLA hidden states to selectively activate language generation only when beneficial, achieving SOTA results with 2.54x inference speedup on driving benchmarks.
-
Test-Time Trajectory Optimization for Autonomous Driving
TOAD applies test-time Cross-Entropy Method optimization to refine trajectories using the planner's scorer as a reward function, improving end-to-end autonomous driving performance without retraining.
-
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
MAPLE proposes latent multi-agent rollouts with supervised fine-tuning followed by reinforcement learning using safety, progress, interaction, and diversity rewards to enable scalable closed-loop training for end-to-end autonomous driving.
-
SimScale: Learning to Drive via Real-World Simulation at Scale
SimScale synthesizes unseen driving states from real logs via neural rendering and reactive environments, generates pseudo-expert trajectories, and shows that co-training on real plus simulated data improves planning robustness and generalization on real benchmarks, with gains scaling by simulation
-
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
AutoVLA unifies semantic reasoning and trajectory planning in one autoregressive VLA model for end-to-end autonomous driving by tokenizing trajectories into discrete actions and using GRPO reinforcement fine-tuning to adaptively reduce unnecessary reasoning.
-
Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling
CaAD adds ego-centric joint-causal modeling and causality-aware policy alignment to end-to-end driving, reporting Driving Score 87.53 and PDMS 91.1 on Bench2Drive and NAVSIM.
-
SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
SpanVLA reduces action generation latency via flow-matching conditioned on history and improves robustness by training on negative-recovery samples with GRPO and a dedicated reasoning dataset.
-
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
DeepSight uses parallel latent feature prediction in BEV for long-horizon world modeling and adaptive text reasoning to reach state-of-the-art closed-loop performance on the Bench2drive benchmark.