By adding future visual state prediction and a dedicated inverse kinematics diffusion network that uses only visual boundary conditions, a 0.5B driving VLA recovers visual grounding and matches 7-8B models on NAVSIM-v2 and nuScenes.
hub Canonical reference
re- gions important for driving
Canonical reference. 71% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 5
baseline 2
citation-polarity summary
years
2026 17representative citing papers
MDrive benchmark shows multi-agent cooperative driving systems generally outperform single-agent ones in closed-loop settings but perception sharing does not always improve planning and negotiation can harm performance in complex traffic.
D³-MoE disentangles style and physical axes with diffusion and self-supervised MoE experts to produce style-controllable trajectories, reporting SOTA 88.2 PDMS on NAVSIM.
IDOL uses inverse dynamics on adjacent predicted latent futures to extract planning-relevant motion deltas, then optimizes trajectories with a closed-loop refinement step, reporting SOTA results on NAVSIM v1 and v2.
NTR adds a self-distillation masked latent reconstruction objective that uses only scene tokens to reconstruct masked patch features, improving visual representation quality and planning performance in end-to-end autonomous driving.
CLOVER is a closed-loop generator-scorer framework that expands proposal coverage with pseudo-expert trajectories and performs conservative self-distillation to achieve state-of-the-art planning scores on NAVSIM and nuScenes.
DriveFuture achieves SOTA results on NAVSIM by conditioning latent world model states on future predictions to directly inform trajectory planning.
FeaXDrive improves end-to-end autonomous driving by shifting diffusion planning to a trajectory-centric formulation with curvature-constrained training, drivable-area guidance, and GRPO post-training, yielding stronger closed-loop performance and feasibility on NAVSIM.
The primary OL-CL gap in end-to-end autonomous driving arises from objective mismatch creating structural inability to model reactive behaviors, which a test-time adaptation method can mitigate.
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.
DIAL expands continuous-action driving policies via intent-conditioned flow matching and multi-intent GRPO, lifting best-of-N preference scores above human demonstrations for the first time on WOD-E2E.
CRAFT is an on-policy RL fine-tuning framework that decomposes closed-loop policy gradients into a group-normalized counterfactual proxy plus residual correction from interaction events, achieving top closed-loop performance on Bench2Drive across multiple driving architectures.
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.
RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.
EvoDriveVLA uses collaborative perception-planning distillation with self-anchor and future-aware teachers to fix perception degradation and long-term instability in driving VLA models, reaching SOTA on nuScenes and NAVSIM.
citing papers explorer
-
Grounding Driving VLA via Inverse Kinematics
By adding future visual state prediction and a dedicated inverse kinematics diffusion network that uses only visual boundary conditions, a 0.5B driving VLA recovers visual grounding and matches 7-8B models on NAVSIM-v2 and nuScenes.
-
MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems
MDrive benchmark shows multi-agent cooperative driving systems generally outperform single-agent ones in closed-loop settings but perception sharing does not always improve planning and negotiation can harm performance in complex traffic.
-
D$^3$-MoE:Dual Disentangled Diffusion Mixture-of-Experts for Style-Controllable End-to-End Autonomous Driving
D³-MoE disentangles style and physical axes with diffusion and self-supervised MoE experts to produce style-controllable trajectories, reporting SOTA 88.2 PDMS on NAVSIM.
-
IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving
IDOL uses inverse dynamics on adjacent predicted latent futures to extract planning-relevant motion deltas, then optimizes trajectories with a closed-loop refinement step, reporting SOTA results on NAVSIM v1 and v2.
-
NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving
NTR adds a self-distillation masked latent reconstruction objective that uses only scene tokens to reconstruct masked patch features, improving visual representation quality and planning performance in end-to-end autonomous driving.
-
CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
CLOVER is a closed-loop generator-scorer framework that expands proposal coverage with pseudo-expert trajectories and performs conservative self-distillation to achieve state-of-the-art planning scores on NAVSIM and nuScenes.
-
DriveFuture: Future-Aware Latent World Models for Autonomous Driving
DriveFuture achieves SOTA results on NAVSIM by conditioning latent world model states on future predictions to directly inform trajectory planning.
-
FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving
FeaXDrive improves end-to-end autonomous driving by shifting diffusion planning to a trajectory-centric formulation with curvature-constrained training, drivable-area guidance, and GRPO post-training, yielding stronger closed-loop performance and feasibility on NAVSIM.
-
BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous Driving
The primary OL-CL gap in end-to-end autonomous driving arises from objective mismatch creating structural inability to model reactive behaviors, which a test-time adaptation method can mitigate.
-
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
-
EponaV2: Driving World Model with Comprehensive Future Reasoning
EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.
-
Driving Intents Amplify Planning-Oriented Reinforcement Learning
DIAL expands continuous-action driving policies via intent-conditioned flow matching and multi-intent GRPO, lifting best-of-N preference scores above human demonstrations for the first time on WOD-E2E.
-
CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
CRAFT is an on-policy RL fine-tuning framework that decomposes closed-loop policy gradients into a group-normalized counterfactual proxy plus residual correction from interaction events, achieving top closed-loop performance on Bench2Drive across multiple driving architectures.
-
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.
-
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
RAD-2 uses a diffusion generator and RL discriminator to cut collision rates by 56% in closed-loop autonomous driving planning.
-
EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
EvoDriveVLA uses collaborative perception-planning distillation with self-anchor and future-aware teachers to fix perception degradation and long-term instability in driving VLA models, reaching SOTA on nuScenes and NAVSIM.
- ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving