Buchumschlag

Stabilizing Information Flow Entropy: Regularization for Safe and Interpretable Autonomous Driving Perception

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yang, Haobo, Zhang, Shiyan, Yang, Zhuoyi, Guo, Jilong, Yang, Jun, Zhang, Xinyu
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving
von: Yang, Haobo, et al.
Veröffentlicht: (2024)

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
von: Zhang, Jiawei, et al.
Veröffentlicht: (2025)

Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
von: Wei, Qi, et al.
Veröffentlicht: (2026)

Gradient-Guided Parameter Mask for Multi-Scenario Image Restoration Under Adverse Weather
von: Guo, Jilong, et al.
Veröffentlicht: (2024)

Reinfier and Reintrainer: Verification and Interpretation-Driven Safe Deep Reinforcement Learning Frameworks
von: Yang, Zixuan, et al.
Veröffentlicht: (2024)

Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarios
von: Zhang, Feihong, et al.
Veröffentlicht: (2025)

Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
von: Wen, Muning, et al.
Veröffentlicht: (2024)

EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
von: Jiao, Siwen, et al.
Veröffentlicht: (2025)

LoRA Dropout as a Sparsity Regularizer for Overfitting Control
von: Lin, Yang, et al.
Veröffentlicht: (2024)

Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
von: Choi, Yunseon, et al.
Veröffentlicht: (2024)

From Imitation to Exploration: End-to-end Autonomous Driving based on World Model
von: Li, Yueyuan, et al.
Veröffentlicht: (2024)

Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving
von: Hu, Xuemin, et al.
Veröffentlicht: (2024)

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
von: Ji, Jiaming, et al.
Veröffentlicht: (2025)

A Variance-Reduced Cubic-Regularized Newton for Policy Optimization
von: Sun, Cheng, et al.
Veröffentlicht: (2025)

HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving
von: Huang, Zilin, et al.
Veröffentlicht: (2024)

Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
von: Fan, Junchao, et al.
Veröffentlicht: (2025)

STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
von: Li, Yingwei, et al.
Veröffentlicht: (2026)

Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
von: Hu, Yuting, et al.
Veröffentlicht: (2025)

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
von: Zhang, Shengjun, et al.
Veröffentlicht: (2026)

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
von: Zeqiao, Li, et al.
Veröffentlicht: (2025)

Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
von: Yang, Haobo, et al.
Veröffentlicht: (2025)

DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization
von: Hu, Chengpeng, et al.
Veröffentlicht: (2026)

Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving
von: Abouelazm, Ahmed, et al.
Veröffentlicht: (2026)

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
von: Yang, Kai, et al.
Veröffentlicht: (2025)

BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
von: Liu, Shu, et al.
Veröffentlicht: (2025)

Driving Reaction Trajectories via Latent Flow Matching
von: Shen, Yili, et al.
Veröffentlicht: (2026)

Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
von: Chen, Rufeng, et al.
Veröffentlicht: (2026)

Skill-based Safe Reinforcement Learning with Risk Planning
von: Zhang, Hanping, et al.
Veröffentlicht: (2025)

GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
von: Lei, Xing, et al.
Veröffentlicht: (2025)

Quantile Geometry Regularization for Distributional Reinforcement Learning
von: Zhang, Zhaofan, et al.
Veröffentlicht: (2026)

Selective Learning: Towards Robust Calibration with Dynamic Regularization
von: Han, Zongbo, et al.
Veröffentlicht: (2024)

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
von: Tayal, Mumuksh, et al.
Veröffentlicht: (2026)

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
von: Zhang, Jiefu, et al.
Veröffentlicht: (2026)

PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework
von: Ding, Zihan, et al.
Veröffentlicht: (2026)

SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation
von: Stoler, Benjamin, et al.
Veröffentlicht: (2024)

ADReFT: Adaptive Decision Repair for Safe Autonomous Driving via Reinforcement Fine-Tuning
von: Cheng, Mingfei, et al.
Veröffentlicht: (2025)

SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
von: Zhang, Hanwei, et al.
Veröffentlicht: (2026)

FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
von: Li, Qizheng, et al.
Veröffentlicht: (2026)

Towards Explainable Traffic Flow Prediction with Large Language Models
von: Guo, Xusen, et al.
Veröffentlicht: (2024)

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
von: Wang, Shenzhi, et al.
Veröffentlicht: (2025)