GuidedWAM: Training-Free Energy Guidance for World Action Models in Autonomous Driving
cs.AI, cs.RO
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Pseudo-Simulation for Autonomous Driving
- Diffusion Posterior Sampling for General Noisy Inverse Problems
- SafeFlow: Safe Robot Motion Planning with Flow Matching via Control Barrier Functions
- DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving
- NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
- On the Guidance of Flow Matching
- Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
- World Models
- Manifold Preserving Guided Diffusion
- Classifier-Free Diffusion Guidance
- GAIA-1: A Generative World Model for Autonomous Driving
- Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving
- ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
- HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
- DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
- GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
- UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
- On a Formal Model of Safe and Scalable Self-driving Cars
- DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents