Weili Nie

发表

Under review as a conference paper at ICLR 2019 softmax Transpose Updated Memory Memory embedded input linear concat Attention Weights concat

Ankit B. Patel, Nina Narodytska, Weili Nie, 2019 .

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Yuke Zhu, Zhiding Yu, Song-Chun Zhu, 2022, International Conference on Learning Representations.

LaRVAE: Label Replacement VAE for Semi-Supervised Disentanglement Learning

Ankit B. Patel, Richard Baraniuk, Weili Nie, 2020 .

Diffusion Models for Adversarial Purification

Anima Anandkumar, Chaowei Xiao, Yujia Huang, 2022, ICML.

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Song-Chun Zhu, Anima Anandkumar, Yuke Zhu, 2022, ICLR.

Retrieval-based Controllable Molecule Generation

Richard Baraniuk, Anima Anandkumar, Chaowei Xiao, 2022, International Conference on Learning Representations.

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Anima Anandkumar, T. Goldstein, De-An Huang, 2022, NeurIPS.

Dynamic-Backbone Protein-Ligand Structure Prediction with Multiscale Generative Diffusion Models

Anima Anandkumar, Weili Nie, Zhuoran Qiao, 2022, ArXiv.

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics

Rick L. Stevens, James J. Davis, Logan T. Ward, 2022, bioRxiv.

PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition

Zhiding Yu, Chaowei Xiao, Weili Nie, 2022, ArXiv.

DensePure: Understanding Diffusion Models towards Adversarial Robustness

D. Song, Anima Anandkumar, Bo Li, 2022, ArXiv.

Fast Sampling of Diffusion Models via Operator Learning

K. Azizzadenesheli, Anima Anandkumar, Weili Nie, 2022, ArXiv.

Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing

Anima Anandkumar, Shengchao Liu, Chaowei Xiao, 2022, Nat. Mac. Intell..

RelGAN: Relational Generative Adversarial Networks for Text Generation

Nina Narodytska, Ankit B. Patel, Weili Nie, 2019, ICLR.

Retrieval-based Controllable Molecule Generation

Richard Baraniuk, Anima Anandkumar, Chaowei Xiao, 2022, ArXiv.

A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations

Yang Zhang, Ankit B. Patel, Ankit Patel, 2018, ICML.

A Text-guided Protein Design Framework

Shengchao Liu, Anima Anandkumar, A. Gitter, 2023, ArXiv.

Controllable and Compositional Generation with Latent-Space Energy-Based Models pdf

Anima Anandkumar, Arash Vahdat, Weili Nie, 2021, NeurIPS.

Fast Sampling of Diffusion Models via Operator Learning

K. Azizzadenesheli, Anima Anandkumar, Weili Nie, 2022, ArXiv.

Retrieval-based Controllable Molecule Generation

Richard Baraniuk, Anima Anandkumar, Chaowei Xiao, 2022, ICLR.

Towards a Better Understanding and Regularization of GAN Training Dynamics

Ankit B. Patel, Weili Nie, Ankit Patel, 2018, UAI.

I$^2$SB: Image-to-Image Schr\"odinger Bridge

E. Theodorou, Anima Anandkumar, De-An Huang, 2023, 2302.05872.

Defending against Adversarial Audio via Diffusion Model

Wei Ping, Chaowei Xiao, Weili Nie, 2023, ICLR.

I2SB: Image-to-Image Schrödinger Bridge

E. Theodorou, Anima Anandkumar, De-An Huang, 2023, ArXiv.

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

Anima Anandkumar, Yuke Zhu, Zhiding Yu, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

QG-net: a data-driven question generation model for educational content

Richard G. Baraniuk, Andrew S. Lan, Andrew E. Waters, 2018, L@S.

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Ankit B. Patel, Anima Anandkumar, Yuke Zhu, 2020, NeurIPS.

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

M. Shoeybi, Bryan Catanzaro, Anima Anandkumar, 2023, ArXiv.

State-specific protein–ligand complex structure prediction with a multiscale deep generative model

Anima Anandkumar, Weili Nie, Zhuoran Qiao, 2022, Nature Machine Intelligence.

I2SB: Image-to-Image Schrödinger Bridge

Evangelos A. Theodorou, E. Theodorou, Anima Anandkumar, 2023, ICML.

R EL V I T: C ONCEPT - GUIDED V ISION T RANSFORMER FOR V ISUAL R ELATIONAL R EASONING

Song-Chun Zhu, Anima Anandkumar, Yuke Zhu, 2022 .

Semi-Supervised StyleGAN for Disentanglement Learning

Ankit B. Patel, Anima Anandkumar, Animesh Garg, 2020, ICML.

Quantification of Myxococcus xanthus Aggregation and Rippling Behaviors: Deep-Learning Transformation of Phase-Contrast into Fluorescence Microscopy Images

Ankit B. Patel, Roy D. Welch, O. Igoshin, 2021, bioRxiv.

Fast Training of Diffusion Models with Masked Transformers

Anima Anandkumar, Weili Nie, Arash Vahdat, 2023, ArXiv.

Fast Sampling of Diffusion Models via Operator Learning

K. Azizzadenesheli, Anima Anandkumar, Weili Nie, 2022, ICML.

An Improved Semi-Supervised VAE for Learning Disentangled Representations pdf

Zichao Wang, Richard G. Baraniuk, Ankit B. Patel, 2020, ArXiv.

Improving Generative Model-based Unfolding with Schrödinger Bridges

B. Nachman, Guan-Horng Liu, Weili Nie, 2023, ArXiv.

User-Centric Cross-Tier Base Station Clustering and Cooperation in Heterogeneous Networks: Rate Improvement and Energy Saving

Shi Jin, Fu-Chun Zheng, Xiaoming Wang, 2016, IEEE Journal on Selected Areas in Communications.

Energy-efficient base station cooperation in downlink heterogeneous cellular networks

Fu-Chun Zheng, Xiaoming Wang, Wenyi Zhang, 2014, 2014 IEEE Global Communications Conference.

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

M. Shoeybi, Bryan Catanzaro, Anima Anandkumar, 2023, EMNLP.