Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving
cs.LG, cs.AI
Submitted: 2026-03-16
Updated: 2026-11-05
Comments: Accepted at NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RIFT: Group-Relative RL Fine-Tuning for Realistic and Controllable Traffic Simulation
- CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
- Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
- Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning
- Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen
- Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
- Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
- LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models
- Steerable Adversarial Scenario Generation through Test-Time Preference Alignment
- Proximal Policy Optimization Algorithms
- E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving
- NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving
- Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving
- Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving
- Robust Reinforcement Learning using Adversarial Populations
- Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving
- Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
- Generative AI for Autonomous Driving: Frontiers and Opportunities
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis