Weiyang Liu

 

Google Scholar   Github   Twitter

 

University of Cambridge
Max Planck Institute for Intelligent Systems

About Me

I am currently conducting research at Cambridge and MPI Tübingen with Adrian Weller and Bernhard Schölkopf. As a member of the advising team at MeshCapade, I also work closely with Michael J. Black. Previously, I spent wonderful years at Georgia Tech. I have also spent time at Google Brain, Nvidia Research, and MERL.

I work on principled modeling of inductive bias in machine learning. My research seeks to understand how inductive bias determines generalization, and to develop "light-yet-sweet" generalizable models: (i) light: conceptually simple in methodology and easy to implement in practice, (ii) sweet: having clear intuitions and non-trivial theoretical guarantees.

Over the years, I always find myself fascinated by geometric invariance, symmetry, structures (graph, causality) and how they can benefit generalization as a guiding principle. Recently, I become very passionate about large language models (general intelligence) and generative modeling of the physicual world (physical intelligence). More specifically, I try to understand how LLMs perform reasoning and how to improve it in various scenarios.

I always believe in two principles in my research: (i) insight must precede application, and (ii) everything should be made as simple as possible, but not simpler. I try to follow certain research values.

    - Focus on creating novel ideas, not publishing papers
    - Follow curiosity and passion, not trends
    - Ideas are not owned, but come with debts to those who came before
    - Ideas become stronger when shared, discussed and criticized
    - Life is surprisingly short, so solve problems that interest and excite you most
    - It is good to be quick, but it is more important to be deep
    - Think like an amateur, do as an expert
    - This is not only about how to do research, but also how to live your life

Students

I take great pleasure to (co-)mentor a few talented and highly motivated students. Mentoring and working with junior students is truely a privilege, and I constantly learn from and get inspired by them. I am fortunate to work with (time-wise order):

   - Yamei Chen (2024 - now)
       - M.S. student at Technical University of Munich
   - Zeju Qiu (2024 - now)
       - Ph.D. student at MPI for Intelligent Systems
   - Tim Z. Xiao (2024 - now)
       - Ph.D. student at University of Tübingen

Alumni list (nothing is more rewarding than seeing my mentees succeed)

     - Gege Gao (2023 - 2024): research intern
         - Ph.D. student at University of Tübingen
     - Zeju Qiu (2022 - 2024): master thesis student
         - M.S. at Technical University of Munich
         - Next: Ph.D. student at MPI for Intelligent Systems
     - Longhui Yu (2022 - 2024): research intern
         - M.S. at Peking University
         - Next: Ph.D. student at University of Toronto
     - Zhen Liu (2017 - 2019, 2022 - 2024): research intern
         - M.S. at Georgia Tech → Ph.D. at Mila & University of Montreal
         - Next: Assistant Professor at Chinese University of Hong Kong, Shenzhen

Recent Highlight

Can Large Language Models Understand Symbolic Graphics Programs?
Zeju Qiu*, Weiyang Liu*, Haiwen Feng*, Zhen Liu**, Tim Z. Xiao**, Katherine M. Collins**, Joshua B. Tenenbaum, Adrian Weller, Michael J. Black, Bernhard Schölkopf

Preprint 2024

arXiv | code | project | bib

  @article{qiu2024sgpbench,
      title={Can Large Language Models Understand Symbolic Graphics Programs?},
      author={Qiu, Zeju and Liu, Weiyang and Feng, Haiwen and Liu, Zhen and Xiao, Tim Z and Collins, Katherine M 
        and Tenenbaum, Joshua B and Weller, Adrian and Black, Michael J and Sch{\"o}lkopf, Bernhard},
      journal={arXiv preprint arXiv:2408.08313},
      year={2024}}

Verbalized Machine Learning: Revisiting Machine Learning with Language Models
Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf, Weiyang Liu

Preprint 2024

arXiv | code | project | bib

  @article{xiao2024verbalized,
      title={Verbalized Machine Learning: Revisiting Machine Learning with Language Models},
      author={Xiao, Tim Z and Bamler, Robert and Sch{\"o}lkopf, Bernhard and Liu, Weiyang},
      journal={arXiv preprint arXiv:2406.04344},
      year={2024}}

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
Zhiqing Sun*, Longhui Yu*, Yikang Shen, Weiyang Liu, Yiming Yang, Sean Welleck, Chuang Gan

NeurIPS 2024

arXiv | code | project | bib

  @article{sun2024easy,
      title={Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision},
      author={Sun, Zhiqing and Yu, Longhui and Shen, Yikang and Liu, Weiyang and Yang, Yiming and Welleck, Sean and Gan, Chuang},
      journal={arXiv preprint arXiv:2403.09472},
      year={2024}}

Publication

Verbalized Machine Learning: Revisiting Machine Learning with Language Models
Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf, Weiyang Liu

Preprint 2024

arXiv | code | project | bib

  @article{xiao2024verbalized,
      title={Verbalized Machine Learning: Revisiting Machine Learning with Language Models},
      author={Xiao, Tim Z and Bamler, Robert and Sch{\"o}lkopf, Bernhard and Liu, Weiyang},
      journal={arXiv preprint arXiv:2406.04344},
      year={2024}}

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Weiyang Liu*, Zeju Qiu*, Yao Feng**, Yuliang Xiu**, Yuxuan Xue**, Longhui Yu**, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf

ICLR 2024

arXiv | code | project | huggingface | openreview | talk | slides | bib

  @InProceedings{liu2024boft,
      author = {Liu, Weiyang and Qiu, Zeju and Feng, Yao and Xiu, Yuliang and Xue, Yuxuan and Yu, Longhui and Feng, Haiwen and Liu, Zhen 
        and Heo, Juyeon and Peng, Songyou and Wen, Yandong and Black, Michael J. and Weller, Adrian and Sch{\"o}lkopf, Bernhard},
      title = {Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization},
      booktitle = {ICLR},
      year = {2024}}

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Longhui Yu, Weisen Jiang, Han Shi, J. Yu, Z. Liu, Yu Zhang, James Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu*

ICLR 2024   Spotlight

arXiv | code | project | huggingface | openreview | bib

  @InProceedings{Yu2024MetaMath,
      title={MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models},
      author={Yu, Longhui and Jiang, Weisen and Shi, Han and Yu, Jincheng and Liu, Zhengying 
        and Zhang, Yu and Kwok, James T and Li, Zhenguo and Weller, Adrian and Liu, Weiyang},
      booktitle={ICLR},
      year={2024}}

Controlling Text-to-Image Diffusion by Orthogonal Finetuning
Zeju Qiu*, Weiyang Liu*, Haiwen Feng, Yuxuan Xue, Yao Feng, Zhen Liu, Dan Zhang, Adrian Weller, Bernhard Schölkopf

NeurIPS 2023

arXiv | code | project | bib

  @InProceedings{Qiu2023OFT,
      title={Controlling Text-to-Image Diffusion by Orthogonal Finetuning},
      author={Qiu, Zeju and Liu, Weiyang and Feng, Haiwen and Xue, Yuxuan and Feng, Yao 
        and Liu, Zhen and Zhang, Dan and Weller, Adrian and Schölkopf, Bernhard},
      booktitle={NeurIPS},
      year={2023}}

Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
Weiyang Liu*, Longhui Yu*, Adrian Weller, Bernhard Schölkopf

ICLR 2023

arXiv | code | openreview | talk | slides | bib

  @InProceedings{Liu2023HUG,
      title={Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap},
      author={Liu, Weiyang and Yu, Longhui and Weller, Adrian and Schölkopf, Bernhard},
      booktitle = {ICLR},
      year={2023}}

MeshDiffusion: Score-based Generative 3D Mesh Modeling
Zhen Liu, Yao Feng, Michael J. Black, Derek Nowrouzezahrai, Liam Paull, Weiyang Liu*

ICLR 2023   Notable Top-25%

arXiv | code | project | openreview | talk | slides | bib

  @InProceedings{Liu2023MeshDiffusion,
      title={MeshDiffusion: Score-based Generative 3D Mesh Modeling},
      author={Liu, Zhen and Feng, Yao and Black, Michael J. and Nowrouzezahrai, Derek 
        and Paull, Liam and Liu, Weiyang},
      booktitle = {ICLR},
      year={2023}}

Structural Causal 3D Reconstruction
Weiyang Liu*, Zhen Liu*, Liam Paull, Adrian Weller, Bernhard Schölkopf

ECCV 2022

arXiv | code | talk | slides | bib

  @InProceedings{Liu2022SCR,
      title={Structural Causal 3D Reconstruction},
      author={Liu, Weiyang and Liu, Zhen and Paull, Liam and Weller, Adrian and Schölkopf, Bernhard},
      booktitle = {ECCV},
      year={2022}}

SphereFace Revived: Unifying Hyperspherical Face Recognition
Weiyang Liu*, Yandong Wen*, Bhiksha Raj, Rita Singh, Adrian Weller

TPAMI 2022

arXiv | code | opensphere | IEEE Xplore | bib

  @article{liu2023spherefacer,
      title={SphereFace Revived: Unifying Hyperspherical Face Recognition},
      author={Liu, Weiyang and Wen, Yandong and Raj, Bhiksha and Singh, Rita and Weller, Adrian},
      journal={IEEE Transactions on Pattern Analysis \& Machine Intelligence},
      volume={45},
      number={02},
      pages={2458--2474},
      year={2023}}

SphereFace2: Binary Classification is All You Need for Deep Face Recognition
Yandong Wen*, Weiyang Liu*, Adrian Weller, Bhiksha Raj, Rita Singh

ICLR 2022   Spotlight

arXiv | code | project | openreview | slides | bib

  @InProceedings{Wen2021SphereFace2,
      title={SphereFace2: Binary Classification is All You Need for Deep Face Recognition},
      author={Wen, Yandong and Liu, Weiyang and Weller, Adrian and Raj, Bhiksha and Singh, Rita},
      booktitle = {ICLR},
      year={2022}}

Iterative Teaching by Label Synthesis
Weiyang Liu*, Zhen Liu*, Hanchen Wang*, Liam Paull, Bernhard Schölkopf, Adrian Weller

NeurIPS 2021   Spotlight

arXiv | code | openreview | talk | slides | video | bib

  @InProceedings{Liu2021LAST,
      title={Iterative Teaching by Label Synthesis},
      author={Liu, Weiyang and Liu, Zhen and Wang, Hanchen and Paull, Liam and Schölkopf, Bernhard and Weller, Adrian},
      booktitle = {NeurIPS},
      year={2021}}

Learning with Hyperspherical Uniformity
Weiyang Liu, Rongmei Lin, Zhen Liu, Li Xiong, Bernhard Schölkopf, Adrian Weller

AISTATS 2021

arXiv | code | talk | slides | bib

  @InProceedings{Liu2021SphereUni,
      title={Learning with Hyperspherical Uniformity},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Xiong, Li and Schölkopf, Bernhard and Weller, Adrian},
      booktitle={AISTATS},
      year={2021}}

Orthogonal Over-Parameterized Training
Weiyang Liu*, Rongmei Lin*, Zhen Liu, James Rehg, Liam Paull, Li Xiong, Le Song, Adrian Weller

CVPR 2021   Oral

arXiv | code | project | talk | slides | bib

  @InProceedings{Liu2021OPT,
      title={Orthogonal Over-Parameterized Training},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Rehg, James M. and Paull, Liam 
       and Xiong, Li and Song, Le and Weller, Adrian},
      booktitle={CVPR},
      year={2021}}

Learning towards Minimum Hyperspherical Energy
Weiyang Liu*, Rongmei Lin*, Zhen Liu*, Lixin Liu*, Zhiding Yu, Bo Dai, Le Song

NeurIPS 2018

arXiv | code | project | sphereface+ | talk | slides | bib

  @InProceedings{LiuNIPS18,
      title={Learning towards Minimum Hyperspherical Energy},
      author={Liu, Weiyang and Lin, Rongmei and Liu, Zhen and Liu, Lixin and Yu, Zhiding and Dai, Bo and Song, Le},
      booktitle={NeurIPS},
      year={2018}}

Deep Hyperspherical Learning
Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, Le Song

NIPS 2017   Spotlight

arXiv | code | project | talk | slides | bib

  @inproceedings{Liu2017NIPS,
      title={Deep Hyperspherical Learning},
      author={Liu, Weiyang and Zhang, Yan-Ming and Li, Xingguo and Yu, Zhiding and Dai, Bo and Zhao, Tuo and Song, Le},
      booktitle={NIPS},
      year={2017}}

Iterative Machine Teaching
Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay, Yu Chen, Linda Smith, James Rehg, Le Song

ICML 2017

arXiv | code | demo | talk | slides | bib

  @inproceedings{Liu2017ICML,
      title={Iterative Machine Teaching},
      author={Liu, Weiyang and Dai, Bo and Humayun, Ahmad and Tay, Charlene and Yu, Chen
       and Smith, Linda B and Rehg, James M and Song, Le},
      booktitle={ICML},
      year={2017}}

SphereFace: Deep Hypersphere Embedding for Face Recognition
Weiyang Liu, Yandong Wen, Zhiding Yu, Ming Li, Bhiksha Raj, Le Song
CVPR 2017   Paper Digest Most Influential Paper

arXiv | code | project | demo | slides | bib

  @InProceedings{Liu2017CVPR,
      title = {SphereFace: Deep Hypersphere Embedding for Face Recognition},
      author = {Liu, Weiyang and Wen, Yandong and Yu, Zhiding and Li, Ming and Raj, Bhiksha and Song, Le},
      booktitle = {CVPR},
      year = {2017}}

Large-Margin Softmax Loss for Convolutional Neural Networks
Weiyang Liu, Yandong Wen, Zhiding Yu, Meng Yang
ICML 2016

arXiv | code | project | talk | slides | bib

  @inproceedings{Liu2016ICML,
      title={Large-Margin Softmax Loss for Convolutional Neural Networks},
      author={Liu, Weiyang and Wen, Yandong and Yu, Zhiding and Yang, Meng},
      booktitle={ICML},
      year={2016}}
Last updated on 27th May 2024.
This site has been visisted Free Web Counter times in total.