6 papers
Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents
Chengyang Gu, Le Zhang, Jingbo Zhou +6
Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diverse digital environments, wher…
A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic
Chengyang Gu, Yuxin Pan, Hui Xiong +1
Model-based reinforcement learning (MBRL) improves sample efficiency by leveraging learned dynamics models for policy optimization. However, the effectiveness of methods such as ac…
Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning
Siyang Li, Yize Chen, Yan Guo +2
Advanced deep learning-based approaches have been actively applied to forecast the spatiotemporal physical dynamics governed by partial differential equations (PDEs), which acts as…
STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order
Chengyang Gu, Yuxin Pan, Hui Xiong +1
Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tas…
SEAL: SEmantic-Augmented Imitation Learning via Language Model
Chengyang Gu, Yuxin Pan, Haotian Bai +2
Hierarchical Imitation Learning (HIL) is a promising approach for tackling long-horizon decision-making tasks. While it is a challenging task due to the lack of detailed supervisor…
Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting
Siyang Li, Yize Chen, Hui Xiong
Forecasting faithful trajectories of multivariate time series from practical scopes is essential for reasonable decision-making. Recent methods majorly tailor generative conditiona…