activity
20232025
most citedA Periodic Bayesian Flow for Material Generation

2 citations · 6 across the 9 of their papers we have counts for

collaborators

9 papers

cs.LG20252 cited

A Periodic Bayesian Flow for Material Generation

Hanlin Wu, Yuxuan Song, Jingjing Gong +6

Generative modeling of crystal data distribution is an important yet challenging task due to the unique periodic physical symmetry of crystals. Diffusion-based methods have shown e…

physics.optics2025

Terahertz electro-optic Kerr effect in LaAlO3

Sergey Kovalev, Changqing Zhu, Anneke Reinold +9

In this letter, we investigate the terahertz (THz) electro-optic Kerr effect (KE) dynamics in LaAlO3 (LAO), a widely used substrate for thin film preparation. We show that the KE d…

cs.AI2025

Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark

Liang He, Yougang Chu, Zhen Wu +3

Benchmarks are crucial for evaluating machine learning algorithm performance, facilitating comparison and identifying superior solutions. However, biases within datasets can lead m…

cs.CV20241 cited

The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning

Yaohui Li, Qifeng Zhou, Haoxing Chen +3

Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by givin…

cs.HC20241 cited

SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Kanzhi Cheng, Qiushi Sun, Yougang Chu +4

Graphical User Interface (GUI) agents are designed to automate complex tasks on digital devices, such as smartphones and desktops. Most existing GUI agents interact with the enviro…

cs.CL20231 cited

M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis

Fei Zhao, Chunhui Li, Zhen Wu +3

Multimodal Aspect-based Sentiment Analysis (MABSA) is a fine-grained Sentiment Analysis task, which has attracted growing research interests recently. Existing work mainly utilizes…