2 citations · 9 across the 20 of their papers we have counts for
14 papers · 1 filter
Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning
Yuxuan Zhou, Yubin Wang, Bin Wang +4
Large language models (LLMs) have shown great promise in the medical domain, achieving strong performance on several benchmarks. However, they continue to underperform in real-worl…
Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control
Zhe Wu, Hongjin Lu, Junliang Xing +10
Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches rely on dire…
Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
Georgios Papoudakis, Thomas Coste, Jianye Hao +2
Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward set…
Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding
Jian Hu, Zixu Cheng, Shaogang Gong +4
Video Temporal Grounding (TG) aims to temporally locate video segments matching a natural language description (a query) in a long video. While Vision-Language Models (VLMs) are ef…
Collab-Solver: Collaborative Solving Policy Learning for Mixed-Integer Linear Programming
Siyuan Li, Yifan Yu, Zhihao Zhang +5
Mixed-integer linear programming (MILP) has been a fundamental problem in combinatorial optimization. Conventional MILP solving mainly relies on carefully designed heuristics embed…
Deep Research Agents: A Systematic Examination And Roadmap
Yuxuan Huang, Yihang Chen, Haozheng Zhang +10
The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to…
Beyond Syntax: Action Semantics Learning for App Agents
Bohan Tang, Dezhao Luo, Jianheng Liu +5
The recent development of Large Language Models (LLMs) enables the rise of App agents that interpret user intent and operate smartphone Apps through actions such as clicking and sc…
AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search
Yu Li, Lehui Li, Zhihao Wu +5
Large language model (LLM) agents have demonstrated strong capabilities across diverse domains, yet automated agent design remains a significant challenge. Current automated agent…
ViMo: A Generative Visual GUI World Model for App Agents
Dezhao Luo, Bohan Tang, Kang Li +6
App agents, which autonomously operate mobile Apps through Graphical User Interfaces (GUIs), have gained significant interest in real-world applications. Yet, they often struggle w…
AppVLM: A Lightweight Vision Language Model for Online App Control
Georgios Papoudakis, Thomas Coste, Zhihao Wu +3
The utilisation of foundation models as smartphone assistants, termed app agents, is a critical research challenge. These agents aim to execute human instructions on smartphones by…
Generative Models in Decision Making: A Survey
Xinyu Shao, Jianping Zhang, Haozhi Wang +9
Generative models have fundamentally reshaped the landscape of decision-making, reframing the problem from pure scalar reward maximization to high-fidelity trajectory generation an…
Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning
Qingyuan Wu, Jianheng Liu, Jianye Hao +2
State-of-the-art (SOTA) reinforcement learning (RL) methods have enabled vision-language model (VLM) agents to learn from interaction with online environments without human supervi…
Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
Yongcheng Zeng, Xinyu Cui, Xuanfa Jin +11
Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement,…
Trajectory World Models for Heterogeneous Environments
Shaofeng Yin, Jialong Wu, Siqiao Huang +4
Heterogeneity in sensors and actuators across environments poses a significant challenge to building large-scale pre-trained world models on top of this low-dimensional sensor info…