Deqian Kong
Contact: deqiankong AT ucla.edu
University of California, Los Angeles, 2019 -
I'm a PhD candidate in Department of Statistics and Data Science, UCLA, advised by Prof. Ying Nian Wu.
Currently, I am interested in generative models, language models and AI for science. My hope is to (1) design efficient and generalizable top-down generative models that enable explicit abstraction (compression), (2) leverage generative models for optimization, planning and scientific discovery.
Research Topics
Latent Plan Transformer: Planning as Latent Variable Inference
Deqian Kong*, Dehong Xu*, Minglu Zhao*, Bo Pang, Jianwen Xie, Andrew Lizarraga, Yuhao Huang, Sirui Xie*, Ying Nian Wu
arXiv:2402.04647 (2024) | Project Page
Dual-Space Optimization: Improved Molecule Sequence Design by Latent Prompt Transformer
Deqian Kong*, Yuhao Huang*, Jianwen Xie*, Edouardo Honig*, Ming Xu, Shuanghong Xue, Pei Lin, Sanping Zhou, Sheng Zhong, Nanning Zheng, Ying Nian Wu
arXiv:2402.17179 (2024) | An extended verision to previous NeurIPS 2023 AI for Science Workshop Paper.
Long-term social interaction context: The key to egocentric addressee detection
Deqian Kong, Furqan Khan, Xu Zhang, Prateek Singhal, Ying Nian Wu
ICASSP 2024 (Work done during my internship at Amazon)
Molecule Design by Latent Space Energy-based Modeling and Gradual Distribution Shifting
Deqian Kong† , Bo Pang† , Tian Han, Ying Nian Wu († Equal contribution)
Diverse and Faithful Knowledge-grounded Dialogue Generation via Sequential Posterior Inference
Yan Xu† , Deqian Kong† , Dehong Xu, Ziwei Ji, Bo Pang, Pascale Fung, Ying Nian Wu (†Equal contribution)
International Conference on Machine Learning (ICML 2023) | Code
A statistical approach to topological entanglement: Boltzmann machine representation of higher-order irreducible correlation
Shi Feng, Deqian Kong, Nandini Trivedi
Unsupervised Meta-learning via Latent Space Energy-based Model of Symbol Vector Coupling
Deqian Kong*, Bo Pang* and Ying Nian Wu (*Equal contribution)
YouRefIt: Embodied Reference Understanding with Language and Gesture
Yixin Chen, Qing Li, Deqian Kong, Yik Lun Kei, Tao Gao, Yixin Zhu, Song-Chun Zhu, Siyuan Huang
International Conference on Computer Vision (ICCV 2021, Oral)
A Benchmark Dataset and Multi-Scale Attention Network for Semantic Traffic Light Detection
Yang Feng*, Deqian Kong*, Ping Wei, Hongbin Sun, Nanning Zheng (*Equal contribution)
IEEE Intelligent Transportation Systems Conference (ITSC 2019)