5 papers
Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation
Zhimin Wang, Meiyuan Zhu, Duo Wu +8
Vision-Language Navigation (VLN) requires agents to continuously ground task progress from long-horizon instructions and partial egocentric observations. Existing VLM-based navigat…
Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training
Linjia Kang, Zhimin Wang, Yongkang Zhang +5
Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensiv…
Grounding Large Language Models as Generalizable Policies in Network Control
Duo Wu, Linjia Kang, Zhimin Wang +9
Designing generalizable control policies that operate reliably under changing conditions is essential for robust network services in modern digital infrastructure. Yet network cont…
Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration
Zhimin Wang, Duo Wu, Shaokang He +6
Effective real-world multi-agent collaboration requires not only accurate planning but also the ability to reason about collaborators' intents--a crucial capability for avoiding mi…
Adapting Differential Molecular Representation with Hierarchical Prompts for Multi-label Property Prediction
Linjia Kang, Songhua Zhou, Shuyan Fang +1
Accurate prediction of molecular properties is crucial in drug discovery. Traditional methods often overlook that real-world molecules typically exhibit multiple property labels wi…