Publications

Our research contributions spanning 2020-2025

25
2025
Naturelm: Deciphering the language of nature for scientific discovery
PreprintRecent
Y Xia, P Jin, S Xie, L He, C Cao, R Luo, G Liu, Y Wang, Z Liu, YJ Chen, et al.
arXiv e-prints7 citations
arXiv PDF
Click to Copy Title
E2Former: A Linear-time Efficient and Equivariant Transformer for Scalable Molecular Modeling
PreprintRecent
Y Li, L Huang, Z Ding, C Wang, X Wei, H Yang, Z Wang, C Liu, Y Shi, et al.
arXiv preprint0 citations
arXiv PDF
Click to Copy Title
Modeling Earth-Scale Human-Like Societies with One Billion Agents
PreprintRecent
H Guan, J He, L Fan, Z Ren, S He, X Yu, Y Chen, S Zheng, TY Liu, Z Liu
arXiv preprint0 citations
arXiv PDF
Click to Copy Title
No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
PreprintRecent
Y Zhang, Z Zhang, H Guan, Y Cheng, Y Duan, C Wang, Y Wang, S Zheng, et al.
arXiv preprint0 citations
arXiv PDF
Click to Copy Title
RedChronos: A Large Language Model-Based Log Analysis System for Insider Threat Detection in Enterprises
PreprintRecent
C Li, Z Zhu, J He, X Zhang
arXiv preprint1 citations
arXiv PDF
Click to Copy Title
Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models
PreprintRecent
H Guan, J He, J Zhang
arXiv preprint0 citations
arXiv PDF
Click to Copy Title
Tracing the Misuse of Personalized Textual Embeddings for Text-to-Image Models
Conference PaperRecent
W Feng, J He, J Zhang, T Wei, W Zhou, Q Guo, W Zhang, T Zhang, N Yu
ICLR 2025 Workshop on Navigating and Addressing Data Problems for Foundation Models0 citations
Click to Copy Title
FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction
Conference PaperRecent
Y Duan, W Wang, J Li
Proceedings of the AAAI Conference on Artificial Intelligence0 citations
Click to Copy Title
Scalable emulation of protein equilibrium ensembles with generative deep learning
Journal ArticleGrowing Interest
S Lewis, T Hempel, J Jiménez-Luna, M Gastegger, Y Xie, AYK Foong, et al.
Science41 citations
Click to Copy Title
24
2024
From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph‐Based Deep Learning
Journal ArticleRecent
Y Min, Y Wei, P Wang, X Wang, H Li, N Wu, S Bauer, S Zheng, Y Shi, et al.
Advanced Science8 citations
Click to Copy Title
Mattersim: A deep learning atomistic model across elements, temperatures and pressures
PreprintMedium Impact
H Yang, C Hu, Y Zhou, X Liu, Y Shi, J Li, G Li, Z Chen, S Chen, C Zeni, et al.
arXiv preprint97 citations
arXiv PDF
Click to Copy Title
Towards Generalist Prompting for Large Language Models by Mental Models
PreprintRecent
H Guan, J He, S Zheng, EH Chen, W Zhang, N Yu
arXiv preprint0 citations
arXiv PDF
Click to Copy Title
Aqualora: Toward white-box protection for customized stable diffusion models via watermark lora
Conference PaperGrowing Interest
W Feng, W Zhou, J He, J Zhang, T Wei, G Li, T Zhang, W Zhang, N Yu
ICML 202431 citations
Click to Copy Title
Predicting equilibrium distributions for molecular systems with deep learning
Journal ArticleHigh Impact
S Zheng, J He, C Liu, Y Shi, Z Lu, W Feng, F Ju, J Wang, J Zhu, Y Min, et al.
Nature Machine Intelligence140 citations
Click to Copy Title
Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
Conference PaperRecent
Y Ren, D Zheng, C Liu, P Jin, Y Shi, L Huang, J He, S Luo, T Qin, TY Liu
NeurIPS 20242 citations
Click to Copy Title
23
2023
Catch you everything everywhere: Guarding textual inversion via concept watermarking
PreprintGrowing Interest
W Feng, J He, J Zhang, T Zhang, W Zhou, W Zhang, N Yu
arXiv preprint11 citations
arXiv PDF
Click to Copy Title
Control risk for potential misuse of artificial intelligence in science
PreprintGrowing Interest
J He, W Feng, Y Min, J Yi, K Tang, S Li, J Zhang, K Chen, W Zhou, X Xie, et al.
arXiv preprint11 citations
arXiv PDF
Click to Copy Title
The impact of large language models on scientific discovery: a preliminary study using gpt-4
PreprintMedium Impact
MR AI4Science, MA Quantum
arXiv preprint70 citations
arXiv PDF
Click to Copy Title
Towards generalizable reinforcement learning for trade execution
PreprintGrowing Interest
C Zhang, Y Duan, X Chen, J Chen, J Li, L Zhao
arXiv preprint12 citations
arXiv PDF
Click to Copy Title
Invertible rescaling network and its extensions
Journal ArticleGrowing Interest
M Xiao, S Zheng, C Liu, Z Lin, TY Liu
International Journal of Computer Vision36 citations
Click to Copy Title
Molecule generation for target protein binding with structural motifs
Conference PaperMedium Impact
Z Zhang, Y Min, S Zheng, Q Liu
The eleventh international conference on learning representations72 citations
Click to Copy Title
22
2022
Quantized training of gradient boosting decision trees
Conference PaperGrowing Interest
Y Shi, G Ke, Z Chen, S Zheng, TY Liu
Advances in neural information processing systems33 citations
Click to Copy Title
Your transformer may not be as powerful as you expect
Conference PaperMedium Impact
S Luo, S Li, S Zheng, TY Liu, L Wang, D He
Advances in Neural Information Processing Systems65 citations
Click to Copy Title
Benchmarking graphormer on large-scale molecular modeling datasets
PreprintMedium Impact
Y Shi, S Zheng, G Ke, Y Shen, J You, J He, S Luo, C Liu, D He, TY Liu
arXiv preprint88 citations
arXiv PDF
Click to Copy Title
Masked molecule modeling: A new paradigm of molecular representation learning for chemistry understanding
PreprintRecent
J He, K Tian, S Luo, Y Min, S Zheng, Y Shi, D He, H Liu, N Yu, L Wang, et al.
arXiv preprint7 citations
Click to Copy Title
One transformer can understand both 2d & 3d molecular data
Conference PaperHigh Impact
S Luo, T Chen, Y Xu, S Zheng, TY Liu, L Wang, D He
ICLR 2022134 citations
Click to Copy Title
Exploring the limits of differentially private deep learning with group-wise clipping
Conference PaperMedium Impact
J He, X Li, D Yu, H Zhang, J Kulkarni, YT Lee, A Backurs, N Yu, J Bian
ICLR 202358 citations
Click to Copy Title
FactorVAE: A probabilistic dynamic factor model based on variational autoencoder for predicting cross-sectional stock returns
Conference PaperMedium Impact
Y Duan, L Wang, Q Zhang, J Li
Proceedings of the AAAI conference on artificial intelligence78 citations
Click to Copy Title
LightGBM: Light gradient boosting machine
PublicationMedium Impact
Y Shi, G Ke, D Soukhavong, J Lamb, Q Meng, T Finley, T Wang, W Chen, et al.
R package version62 citations
Click to Copy Title
21
2021
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
Conference PaperMedium Impact
S Luo, S Li, T Cai, D He, D Peng, S Zheng, G Ke, L Wang, TY Liu
Advances in Neural Information Processing Systems, 2021 (NeurIPS 2021)60 citations
Click to Copy Title
How could Neural Networks understand Programs?
Conference PaperMedium Impact
D Peng, S Zheng, Y Li, G Ke, D He, TY Liu
Proceedings of International Conference on Machine Learning (ICML)75 citations
Click to Copy Title
Do Transformers Really Perform Badly for Graph Representation?
Conference PaperHigh Impact
C Ying, T Cai, S Luo, S Zheng, G Ke, D He, Y Shen, TY Liu
Thirty-Fifth Conference on Neural Information Processing Systems (NIPS)1760 citations
Click to Copy Title
20
2020
Modeling Lost Information in Lossy Image Compression
PreprintGrowing Interest
Y Wang, M Xiao, C Liu, S Zheng, TY Liu
arXiv preprint32 citations
arXiv PDF
Click to Copy Title
Deep learning for prediction of the air quality response to emission changes
Journal ArticleHigh Impact
J Xing, S Zheng, D Ding, JT Kelly, S Wang, S Li, T Qin, M Ma, Z Dong, et al.
Environmental science & technology116 citations
Click to Copy Title
Invertible Image Rescaling
Conference PaperHigh Impact
M Xiao, S Zheng, C Liu, Y Wang, D He, G Ke, J Bian, Z Lin, TY Liu
European Conference on Computer Vision (ECCV) 2020309 citations
Click to Copy Title
Cross-Iteration Batch Normalization
Conference PaperHigh Impact
Z Yao, Y Cao, S Zheng, G Huang, S Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)154 citations
Click to Copy Title
On layer normalization in the transformer architecture
Conference PaperHigh Impact
R Xiong, Y Yang, D He, K Zheng, S Zheng, C Xing, H Zhang, Y Lan, et al.
Proceedings of the 37th International Conference on Machine Learning1360 citations
Click to Copy Title
18
2018
Gradient boosting with piece-wise linear regression trees
Conference PaperMedium Impact
Y Shi, J Li, Z Li
International Joint Conferences on Artificial Intelligence75 citations
Click to Copy Title
Capacity control of relu neural networks by basis-path norm
Conference PaperGrowing Interest
S Zheng, Q Meng, H Zhang, W Chen, N Yu, TY Liu
Proceedings of the 33rd AAAI Conference on Artificial Intelligence27 citations
Click to Copy Title
π-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Conference PaperGrowing Interest
Q Meng, S Zheng, H Zhang, W Chen, Q Ye, ZM Ma, TY Liu
Proceedings of the 7th International Conference on Learning Representations40 citations
Click to Copy Title
17
2017
Asynchronous stochastic gradient descent with delay compensation
Conference PaperHigh Impact
S Zheng, Q Meng, T Wang, W Chen, N Yu, ZM Ma, TY Liu
Proceedings of the 34th International Conference on Machine Learning, PMLR406 citations
Click to Copy Title

Publications

Naturelm: Deciphering the language of nature for scientific discovery

E2Former: A Linear-time Efficient and Equivariant Transformer for Scalable Molecular Modeling

Modeling Earth-Scale Human-Like Societies with One Billion Agents

No Free Lunch: Rethinking Internal Feedback for LLM Reasoning

RedChronos: A Large Language Model-Based Log Analysis System for Insider Threat Detection in Enterprises

Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models

Tracing the Misuse of Personalized Textual Embeddings for Text-to-Image Models

FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction

Scalable emulation of protein equilibrium ensembles with generative deep learning

From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph‐Based Deep Learning

Mattersim: A deep learning atomistic model across elements, temperatures and pressures

Towards Generalist Prompting for Large Language Models by Mental Models

Aqualora: Toward white-box protection for customized stable diffusion models via watermark lora

Predicting equilibrium distributions for molecular systems with deep learning

Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning

Catch you everything everywhere: Guarding textual inversion via concept watermarking

Control risk for potential misuse of artificial intelligence in science

The impact of large language models on scientific discovery: a preliminary study using gpt-4

Towards generalizable reinforcement learning for trade execution

Invertible rescaling network and its extensions

Molecule generation for target protein binding with structural motifs

Quantized training of gradient boosting decision trees

Your transformer may not be as powerful as you expect

Benchmarking graphormer on large-scale molecular modeling datasets

Masked molecule modeling: A new paradigm of molecular representation learning for chemistry understanding

One transformer can understand both 2d & 3d molecular data

Exploring the limits of differentially private deep learning with group-wise clipping

FactorVAE: A probabilistic dynamic factor model based on variational autoencoder for predicting cross-sectional stock returns

LightGBM: Light gradient boosting machine

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

How could Neural Networks understand Programs?

Do Transformers Really Perform Badly for Graph Representation?

Modeling Lost Information in Lossy Image Compression

Deep learning for prediction of the air quality response to emission changes

Invertible Image Rescaling

Cross-Iteration Batch Normalization

On layer normalization in the transformer architecture

Gradient boosting with piece-wise linear regression trees

Capacity control of relu neural networks by basis-path norm

π-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space

Asynchronous stochastic gradient descent with delay compensation