6 papers
DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
Xucong Wang, Zhe Zhao, Liheng Yu +3
Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding agents, where the execution feedback from compilation and tests provides…
FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models
Xucong Wang, Pengkun Wang, Zhe Zhao +3
Multi-Label Recognition (MLR) based on Vision-Language Models (VLMs) aims to leverage their pre-trained knowledge to better adapt complex recognition scenarios, thereby enhancing m…
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
Liheng Yu, Zhe Zhao, Yuxuan Wang +4
Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be fo…
Rethinking Crystal Symmetry Prediction: A Decoupled Perspective
Liheng Yu, Zhe Zhao, Xucong Wang +2
Efficiently and accurately determining the symmetry is a crucial step in the structural analysis of crystalline materials. Existing methods usually mindlessly apply deep learning m…
Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
Zhongchao Yi, Zhengyang Zhou, Qihe Huang +4
Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distributi…
A Powder Diffraction-AI Solution for Crystalline Structure
Di Wu, Pengkun Wang, Shiming Zhou +8
Determining the atomic-level structure of crystalline solids is critically important across a wide array of scientific disciplines. The challenges associated with obtaining samples…