Long Wei*, Peiyan Hu*, Ruiqi Feng*, Haodong Feng, Yixuan Du, Tao Zhang, Rui Wang, Yue Wang, Zhi-Ming Ma, Tailin Wu

NeurIPS2024; Oral at ICLR 2024 AI4PDE workshop

We introduce a novel method for controlling complex physical systems using generative models, by minimizing the learned generative energy function and specified objective

ML for design

Tailin Wu*, Takashi Maruyama*, Long Wei*, Tao Zhang*, Yilun Du*, Gianluca Iaccarino, Jure Leskovec

ICLR2024 Spotlight

We introduce a method that uses compositional generative models to design boundaries and initial states significantly more complex than the ones seen in training for physical simulations

ML for simulation

Haixin Wang*, Jiaxin Li*, Anubhav Dwivedi, Kentaro Hara, Tailin Wu

ICLR2024

We introduce a boundary-embedded neural operator that incorporates complex boundary shape and inhomogeneous boundary values into the solving of Elliptic PDEs

ML for simulation

Tailin Wu*, Willie Neiswanger*, Hongtao Zheng*, Stefano Ermon, Jure Leskovec

AAAI2024 Oral (top 10% of accepted papers)

We introduced uncertainty quantification method for forward simulation and inverse problems of PDEs using latent uncertainty propagation.

ML for simulation

Tailin Wu* , Takashi Maruyama*, Qingqing Zhao*, Gordon Wetzstein, Jure Leskovec

ICLR2023 notable top-25%

Best poster award at SUPR

We introduced the first fully deep learning-based surrogate models for physical simulations that jointly learn forward prediction and optimizes computational cost with RL.

ML for simulation

Xuan Zhang, … Tailin Wu (31th/63 author), … Shuiwang Ji

*Review paper summarizing the key challenges, current frontiers, and open questions of AI4Science, for quantum, atomistic, and continuum systems.*

ML for simulation

Tailin Wu, Takashi Maruyama, Jure Leskovec

NeurIPS2022

We introduced a method for accelerating forward simulation and inverse optimization of PDEs via latent global evolution, achieving up to 15x speedup while achieving competitive accuracy w.r.t. SOTA models.

ML for simulation

Tailin Wu, Qinchen Wang, Yinan Zhang, Rex Ying, Kaidi Cao, Rok Sosič, Ridwan Jalali, Hassan Hamam, Marko Maucec, Jure Leskovec

SIGKDD2022 & ICLR AI for Earth and Space Sciences Workshop long contributed talk

We introduced a hybrid GNN-based surrogate model for large-scale fluid simulation, with up to 18x speedup and scale to over 3D, 10^6 cells per time step (100x higher than prior models).

ML for discovery

Tailin Wu, Megan Tjandrasuwita, Zhengxuan Wu, Xuelin Yang, Kevin Liu, Rok Sosič, Jure Leskovec

NeurIPS2022

We introduce a neuro-symbolic method that trained with simpler concepts and relations, can zero-shot generalize to more complex, hierarchical concepts, and transfer the knowledge across domains.

ML for simulation

Tailin Wu, Michael Sun, H.G. Jason Chou, Pranay Reddy Samala, Sithipont Cholsaipant, Sophia Kivelson, Jacqueline Yau, Zhitao Ying, E. Paulo Alves, Jure Leskovec†, Frederico Fiuza†

NeurIPS 2022 AI4Science workshop, also under review

We introduced a hybrid particle-continuum representation for simulation of multi-scale, non-equilibrium, N-body physical systems, speeding up laser-plasma simulation by 8-fold with 6.8-fold error reduction.

Representation Learning

Tailin Wu*, Hongyu Ren*, Pan Li, Jure Leskovec

NeurIPS 2020

Featured in Synced AI Technology & Industry Review (机器之心)

We introduced Graph Information Bottleneck, a principle and representation learning method for learning minimum sufficient information from graph-structured data, significantly improving GNN’s robustness to adversarial attacks and random noise.

representation learning

ICLR2020We theoretically analyzed the Information Bottleneck objective, to understand and predict observed phase transitions (sudden jumps in accuracy) in the prediction vs. compression tradeoff.

ML for discovery

Tailin Wu, Max Tegmark

**Physical Review** E 100 (3), 033311

Featured in MIT Technology Review and Motherboard

Featured in PRE Spotlight on Machine Learning in Physics

We introduced a paradigm and algorithms for learning theories (small, interpretable models together with domain classifier) each specializing in explaining aspects of a dynamical system. It combines four inductive biases from physicists: divide-and-conquer, Occam’s razor with MDL, unification and lifelong learning.

ML for discovery

Tailin Wu,Thomas Breuel, Michael Skuhersky, Jan Kautzin

Best Poster Award at

ICML2019 Time Series Workshop

We introduced a method for inferring Granger causal relations for large-scale, nonlinear time series with only observational data.

representation learning

2020, 22(1), 7, as cover issue. arXiv:1908.08961.EntropyWe introduce an algorithm for discovering the Pareto frontier of compression vs. prediction tradeoff in binary classification of neural networks.

representation learning

Tailin Wu, Ian Fischer, Isaac Chuang, Max Tegmark

UAI2019, Tel Aviv, Israel

21(10), 924 (Extended version)Entropy

ICLR 2019 Learning with Limited Data workshop as spotlight

We theoretically derive the condition of learnability in the compression vs. prediction tradeoff in the Information Bottleneck objective.

ML for discovery

Silviu-Marian Udrescu, Andrew Tan, Jiahai Feng, Orisvaldo Neto, Tailin Wu, Max Tegmark

NeurIPS2020, Oral

We introduce a state-of-the-art symbolic regression algorithm that robustly re-discovering top 100 physics equations from noisy data from Feynman lectures.

representation learning

Curtis G. Northcutt*, Tailin Wu*, Isaac Chuang

UAI2017 Cleanlab is built on top of it.We introduce a rank pruning method for classification with noisy labels, which provably obtains similar performance as without label noise.

ML for discovery

Daniel Zeng*, Tailin Wu*, Jure Leskovec

ICML2022Workshopof Beyond Bayes: Paths Towards Universal Reasoning Systems

We introduce a method that discovers common relational structures (analogical reasoning) from few-shot examples.

ML for discovery

Michael Skuhersky, Tailin Wu, Eviatar Yemini, Amin Nejatbakhsh, Edward Boyden, Max Tegmark

BMC bioinformatics23 (1), 1-18

We introduce a method for identifying the neuron ID in C. elegans and introduced a more accurate neuron atlas with the NeuroPAL technique.