SCORP delivers 10-28% gains in safety and 2-7% in efficiency metrics on WOMD by using dual-path scene conditioning in diffusion planning plus variance-gated group-relative policy optimization for closed-loop stability.
Versatile behavior diffusion for generalized traffic agent simulation
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ECoSim adds multi-modal controllability to pretrained diffusion and autoregressive traffic models via identity-initialized FiLM layers while using less than 1% paired control data on Waymo Open Sim Agents Challenge.
Diff2SP is a diffusion-based generative model that embeds stochastic optimization objectives into scenario generation and supplies regret bounds plus sample-complexity guarantees relative to GANs.
STRELGen combines a multi-agent diffusion model with differentiable STREL specifications to optimize latent space for generating plausible yet safety-critical driving scenarios.
EvoQRE models bounded-rationality traffic as general-sum Markov games solved via QRE and entropy-regularized replicator dynamics, with a proven convergence rate and SOTA results on Waymo and nuPlan.
CRAFT reduces collisions by 31.2% and traffic violations by 33.2% in closed-loop traffic simulation by discovering context-induced failures in what-if rollouts and using a contextual preference evaluator to reweight autoregressive decoding toward globally coherent behaviors.
Proposal-conditioned latent diffusion generates controllable closed-loop traffic scenarios with improved efficiency and test-time guidance on the Waymo Open Motion Dataset.
Self-play RL regularized with 30 minutes of human data produces driving policies that coordinate with humans, training in 15 hours on one GPU with 2500x less data than imitation learning.
The paper proposes a unified risk map modeling and learning framework integrated with diffusion-based adversarial scenario generation for risk-aware planning in partially observable autonomous driving, demonstrating improved time-to-collision metrics on the Waymo Open Motion Dataset.
RLFTSim uses RL fine-tuning on a pre-trained model with a balanced reward to align traffic simulator rollouts to real data distributions and distill goal-conditioned controllability, reporting SOTA realism on the Waymo Open Motion Dataset.
OWMDrive combines multi-step 3D occupancy forecasting with diffusion planning to produce more foresighted trajectories in autonomous driving.
citing papers explorer
-
SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving
SCORP delivers 10-28% gains in safety and 2-7% in efficiency metrics on WOMD by using dual-path scene conditioning in diffusion planning plus variance-gated group-relative policy optimization for closed-loop stability.
-
ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation
ECoSim adds multi-modal controllability to pretrained diffusion and autoregressive traffic models via identity-initialized FiLM layers while using less than 1% paired control data on Waymo Open Sim Agents Challenge.
-
Diff2SP: Diffusion Models for Correlated Scenario Generation in Stochastic Programming
Diff2SP is a diffusion-based generative model that embeds stochastic optimization objectives into scenario generation and supplies regret bounds plus sample-complexity guarantees relative to GANs.
-
Guiding Neuro-Symbolic Scenario Generation with Spatio-Temporal Logic
STRELGen combines a multi-agent diffusion model with differentiable STREL specifications to optimize latent space for generating plausible yet safety-critical driving scenarios.
-
EvoQRE: Modeling Bounded Rationality in Safety-Critical Traffic Simulation via Evolutionary Quantal Response Equilibrium
EvoQRE models bounded-rationality traffic as general-sum Markov games solved via QRE and entropy-regularized replicator dynamics, with a proven convergence rate and SOTA results on Waymo and nuPlan.
-
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
CRAFT reduces collisions by 31.2% and traffic violations by 33.2% in closed-loop traffic simulation by discovering context-induced failures in what-if rollouts and using a contextual preference evaluator to reweight autoregressive decoding toward globally coherent behaviors.
-
Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation
Proposal-conditioned latent diffusion generates controllable closed-loop traffic scenarios with improved efficiency and test-time guidance on the Waymo Open Motion Dataset.
-
Human-like autonomy emerges from self-play and a pinch of human data
Self-play RL regularized with 30 minutes of human data produces driving policies that coordinate with humans, training in 15 hours on one GPU with 2500x less data than imitation learning.
-
Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments
The paper proposes a unified risk map modeling and learning framework integrated with diffusion-based adversarial scenario generation for risk-aware planning in partially observable autonomous driving, demonstrating improved time-to-collision metrics on the Waymo Open Motion Dataset.
-
RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning
RLFTSim uses RL fine-tuning on a pre-trained model with a balanced reward to align traffic simulator rollouts to real data distributions and distill goal-conditioned controllability, reporting SOTA realism on the Waymo Open Motion Dataset.
-
OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model
OWMDrive combines multi-step 3D occupancy forecasting with diffusion planning to produce more foresighted trajectories in autonomous driving.
- Optimization-Guided Diffusion for Interactive Scene Generation