Zhenghao Peng
15 papers · 2021–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Gold πΊοΈ Taxonomy Completionist (26)
π§
Keyword Pioneer
π€
Dynamic Duo
(12)
ποΈ
Keyword Collector
(78)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(10)
Reinforcement Learning
(6)
Computer Vision
(5)
Applications Β· Reinforcement Learning
(5)
Methods
(5)
Domain-Specific
(4)
Deep Learning
(2)
Robotics
(2)
Capabilities
(2)
Machine Learning
(1)
Analysis
(1)
Applications Β· Computer Vision
(1)
Architectures
(1)
Generation
(1)
Keywords
reinforcement learning
(3)
autonomous driving
(3)
safe driving
(2)
diffusion model
(2)
autonomous vehicle
(2)
policy optimization
(1)
imitation learning
(1)
sample efficiency
(1)
trajectory prediction
(1)
off-policy reinforcement learning
(1)
human-in-the-loop learning
(1)
bird's eye view
(1)
embodied ai
(1)
constrained optimization
(1)
offline reinforcement learning
(1)
robotics control
(1)
continuous control
(1)
visual question answering
(1)
synthetic data generation
(1)
human-robot interaction
(1)
Papers
Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning
CVPR 2026
Embodied Scene Understanding for Vision Language Models via MetaVQA
CVPR 2025
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
ICML 2025
Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
CVPR 2025
Improving Agent Behaviors with RL Fine-tuning for Autonomous Driving
ECCV 2024
Shared Autonomy with IDA: Interventional Diffusion Assistance
NeurIPS 2024
SimGen: Simulator-conditioned Driving Scene Generation
NeurIPS 2024
CAT: Closed-loop Adversarial Training for Safe End-to-End Driving
CoRL 2023
Guarded Policy Optimization with Imperfect Online Demonstrations
ICLR 2023
Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
ICLR 2022
Human-AI Shared Control via Policy Dissection
NeurIPS 2022
Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining
ECCV 2022
SwinTextSpotter: Scene Text Spotting via Better Synergy Between Text Detection and Text Recognition
CVPR 2022
Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization
NeurIPS 2021
Safe Driving via Expert Guided Policy Optimization
CoRL 2021