5 papers
AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation
Shanwei Fan, Bin Zhang, Zhiwei Xu +4
Aerial Vision-and-Language Navigation requires drones to follow natural-language instructions and navigate through complex urban environments. Accurate navigation relies on both lo…
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation
Haodong Li, Chunmei Qing, Huanyu Zhang +11
Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) r…
Subgoal Graph-Augmented Planning for LLM-Guided Open-World Reinforcement Learning
Shanwei Fan, Bin Zhang, Zhiwei Xu +4
Large language models (LLMs) offer strong high-level planning capabilities for reinforcement learning (RL) by decomposing tasks into subgoals. However, their practical utility is l…
Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models
Zhenjiang Mao, Siqi Dai, Yuang Geng +1
A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems. However, the existing world models re…
CLeaRForecast: Contrastive Learning of High-Purity Representations for Time Series Forecasting
Jiaxin Gao, Yuxiao Hu, Qinglong Cao +2
Time series forecasting (TSF) holds significant importance in modern society, spanning numerous domains. Previous representation learning-based TSF algorithms typically embrace a c…