Profiles2023-2026
Zihao Wang
Peking University
12Papers
0Last author
21Unique co-authors
5First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers12
- OpenHA: A Series of Open-Source Hierarchical Agentic Models in MinecraftAuthor 1 of 7ICML 2026 · 8 citations
- CREATE: Cross-Layer Resilience Characterization and Optimization for Efficient yet Reliable Embodied AI SystemsAuthor 6 of 12ASPLOS 2026 · 1 citation
- DeepHA: Scaling Action Chains Elicits Deep Hierarchical AgentsAuthor 1 of 7ICML 2026
- Training One Model to Master Cross-Level Agentic Actions via Reinforcement LearningAuthor 2 of 5CVPR 2026
- Open-World Skill Discovery from Unsegmented Demonstration VideosAuthor 2 of 5ICCV 2025 · 5 citations
- GROOT-2: Weakly Supervised Multimodal Instruction Following AgentsAuthor 3 of 7ICLR 2025
- ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context PromptingAuthor 2 of 7CVPR 2025
- GROOT: Learning to Follow Instructions by Watching Gameplay VideosAuthor 3 of 9ICLR 2024 · 43 citations
- OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following AgentsAuthor 1 of 11NeurIPS 2024 · 37 citations
- Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task AgentsAuthor 1 of 7NeurIPS 2023 · 178 citations
- Learning Transformation-Predictive Representations for Detection and Description of Local FeaturesAuthor 1 of 4CVPR 2023
- Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon PredictionAuthor 2 of 5CVPR 2023
