Haihan Gao — accepted AI-conference papers

2026

Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation

Yu Zhong, Zihao Zhang, Rui Zhang, Lingdong Huang, Haihan Gao, Shuo Wang +6

AAAI 2026technical

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Desp

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Prompt-based Visual Alignment for Zero-shot Policy Transfer

Haihan Gao, Rui Zhang, Qi Yi, Hantao Yao, Haochen Li, Jiaming Guo +10

ICML 2024poster

Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified cross-domain representation and resulting in performance degradatio…

Cited by 0 Source ↗PDF ↗Scholar ↗