AIConfPaper
← Search

Wuyang Chen

26 accepted papers

2026

FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction

Yuqiu Liu, Jialin Song, Marissa Ramirez de Chanlatte, Rochishnu Chowdhury, Rushil Paresh Desai, Wuyang Chen +2
CVPR 2026

Real objects that inhabit the physical world follow physical laws and thus behave plausibly during interaction with other physical objects. However, current methods that perform 3D reconstructions of real-world scenes from multi-view 2D images optimize primarily for visual fidelity, i.e., they train

Cited by 0Source ↗code ↗Scholar ↗
2026

Lean Finder: Semantic Search for Mathlib That Understands User Intents

Jialin Lu, Kye Emond, Kaiyu Yang, Swarat Chaudhuri, Weiran Sun, Wuyang Chen
ICLR 2026poster

We present Lean Finder, a semantic search engine for Lean and mathlib that understands and aligns with the intents of mathematicians. Progress in formal theorem proving is often hindered by the difficulty of locating relevant theorems and the steep learning curve of the Lean 4 language, making advan…

Cited by 0Source ↗code ↗Scholar ↗
2026

Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge

Siying Ma, Mehrdad Momeni Zadeh, Mauricio Soroco, Wuyang Chen, Jiguo Cao, Vijay Ganesh
ICLR 2026poster

Recent advances in scientific machine learning (SciML) have enabled neural operators (NOs) to serve as powerful surrogates for modeling the dynamic evolution of physical systems governed by partial differential equations (PDEs). While existing approaches focus primarily on learning simulations from…

Cited by 0Source ↗Scholar ↗
2026

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety

Jialin Song, Xiaodong Liu, Weiwei Yang, Wuyang Chen, Mingqian Feng, Xuekai Zhu +1
ICML 2026poster

We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than single-turn jailbreaks. Existing multi-turn benchmarks are lim…

Cited by 0Source ↗Scholar ↗
2025

On the Role of Label Noise in the Feature Learning Process

Andi Han, Wei Huang, Zhanpeng Zhou, Gang Niu, Wuyang Chen, Junchi Yan +2
ICML 2025poster

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each sample comprises a label-dependent signal and label-indepen…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs

Mauricio Soroco, Jialin Song, Mengzhou Xia, Kye Emond, Weiran Sun, Wuyang Chen
ICML 2025poster

We present PDE-Controller, a framework that enables large language models (LLMs) to control systems governed by partial differential equations (PDEs). Traditional LLMs have excelled in commonsense reasoning but fall short in rigorous logical reasoning. While recent AI-for-math has made strides in pu…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning

Wuyang Chen, Jialin Song, Pu Ren, Shashank Subramanian, Dmitriy Morozov, Michael W. Mahoney
NeurIPS 2024poster

Recent years have witnessed the promise of coupling machine learning methods and physical domain-specific insights for solving scientific problems based on partial differential equations (PDEs). However, being data-intensive, these methods still require a large amount of PDE data. This reintroduces…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2024

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models

Sheng Shen, Le Hou, Yanqi Zhou, Nan Du, Shayne Longpre, Jason Wei +14
ICLR 2024poster

Sparse Mixture-of-Experts (MoE) is a neural architecture design that adds learnable parameters to Large Language Models (LLMs) without increasing computational complexity (FLOPs). Instruction tuning is a technique for training LLMs to follow instructions. We advocate combining these two approaches,…

Cited by 78Source ↗PDF ↗Scholar ↗
2024

Principled Architecture-aware Scaling of Hyperparameters

Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin
ICLR 2024poster

Training a high-quality deep neural network requires choosing suitable hyperparameters, which is a non-trivial and expensive process. Current works try to automatically optimize or design principles of hyperparameters, such that they can generalize to diverse unseen scenarios. However, most designs…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Transferable and Principled Efficiency for Open-Vocabulary Segmentation

Jingxuan Xu, Wuyang Chen, Yao Zhao, Yunchao Wei
CVPR 2024poster

Recent success of pre-trained foundation vision-language models makes Open-Vocabulary Segmentation (OVS) possible. Despite the promising performance this approach introduces heavy computational overheads for two challenges: 1) large model sizes of the backbone; 2) expensive costs during the fine-tun…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2023

Lifelong Language Pretraining with Distribution-Specialized Experts

Wuyang Chen, Yanqi Zhou, Nan Du, Yanping Huang, James Laudon, Zhifeng Chen +1
ICML 2023poster

Pretraining on a large-scale corpus has become a standard method to build general language models (LMs). Adapting a model to new data distributions targeting different downstream tasks poses significant challenges. Naive fine-tuning may incur catastrophic forgetting when the over-parameterized LMs o…

Cited by 59Source ↗PDF ↗Scholar ↗
2022

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation

Wuyang Chen, Xianzhi Du, Fan Yang, Lucas Beyer, Xiaohua Zhai, Tsung-Yi Lin +5
ECCV 2022poster

"This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to object detection and dense prediction tasks, many works inheri…

Cited by 65Source ↗PDF ↗Scholar ↗
2022

Auto-scaling Vision Transformers without Training

Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou
ICLR 2022poster

This work targets automated designing and scaling of Vision Transformers (ViTs). The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution co…

Cited by 36Source ↗PDF ↗code ↗Scholar ↗
2022

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang
NeurIPS 2022accept

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those topological compositions are empirically effective and observed…

Cited by 11Source ↗PDF ↗Scholar ↗
2022

Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining

Miao Lu, Xiaolong Luo, Tianlong Chen, Wuyang Chen, Dong Liu, Zhangyang Wang
ICLR 2022spotlight

We present a novel framework to train a large deep neural network (DNN) for only $\textit{once}$, which can then be pruned to $\textit{any sparsity ratio}$ to preserve competitive accuracy $\textit{without any re-training}$. Conventional methods often require (iterative) pruning followed by re-train…

Cited by 41Source ↗PDF ↗Scholar ↗
2021

Contrastive Syn-to-Real Generalization

Wuyang Chen, Zhiding Yu, Shalini De Mello, Sifei Liu, Jose M. Alvarez, Zhangyang Wang +1
ICLR 2021poster

Training on synthetic data can be beneficial for label or data-scarce scenarios. However, synthetically trained models often suffer from poor generalization in real domains due to domain gaps. In this work, we make a key observation that the diversity of the learned feature embeddings plays an impor…

Cited by 59Source ↗PDF ↗code ↗Scholar ↗
2021

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective

Wuyang Chen, Xinyu Gong, Zhangyang Wang
ICLR 2021poster

Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to trun…

Cited by 331Source ↗PDF ↗code ↗Scholar ↗
2020

AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks

Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li, Yingyan Lin, Zhangyang Wang
ICML 2020poster

The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement and editing. However, compared to the substantial efforts to compressing other de…

Cited by 113Source ↗PDF ↗code ↗Scholar ↗
2020

Automated Synthetic-to-Real Generalization

Wuyang Chen, Zhiding Yu, Zhangyang Wang, Animashree Anandkumar
ICML 2020poster

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pretrained representation. Yet the role of ImageNet knowledge is seldom discussed despite common practices that leverage this knowledge to maintain th…

Cited by 88Source ↗PDF ↗code ↗Scholar ↗
2020

FasterSeg: Searching for Faster Real-time Semantic Segmentation

Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
ICLR 2020poster

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a novel and broader search space integrating multi-resolution…

Cited by 255Source ↗code ↗Scholar ↗
2020

Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training

Xuxi Chen, Wuyang Chen, Tianlong Chen, Ye Yuan, Chen Gong, Kewei Chen +1
ICML 2020poster

Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i.e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples. While current state-of-the-art methods employ importance reweighting to design various biased or unbi…

Cited by 113Source ↗PDF ↗code ↗Scholar ↗
2019

ABD-Net: Attentive but Diverse Person Re-Identification

Tianlong Chen, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang +2
ICCV 2019poster

Attention mechanisms have been found effective for person re-identification (Re-ID). However, the learned "attentive" features are often not naturally uncorrelated or "diverse", which compromises the retrieval performance based on the Euclidean distance. We advocate the complementary powers of atten…

Cited by 672PDF ↗code ↗Scholar ↗
2019

Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images

Wuyang Chen, Ziyu Jiang, Zhangyang Wang, Kexin Cui, Xiaoning Qian
CVPR 2019oral

Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultra-high resolution image, or crop it into small patches for separate process…

Cited by 208PDF ↗code ↗Scholar ↗