AIConfPaper
← Search

Runzhong Wang

27 accepted papers

2026

FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time

Montgomery Bohde, Hongxuan Liu, Mrunali Manjrekar, Magdalena Lederbauer, Shuiwang Ji, Runzhong Wang +1
ICML 2026poster

Tandem mass spectrometry is prominent in scientific discovery workflows for identifying unknown small molecules, yet high-throughput structural elucidation remains challenging. While recent autoregressive and graph diffusion models have shown promise in *de novo* elucidation, performance remains lim…

Cited by 0Source ↗Scholar ↗
2025

DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra

Montgomery Bohde, Mrunali Manjrekar, Runzhong Wang, Shuiwang Ji, Connor W. Coley
ICML 2025poster

Mass spectrometry plays a fundamental role in elucidating the structures of unknown molecules and subsequent scientific discoveries. One formulation of the structure elucidation task is the conditional *de novo* generation of molecular structure given a mass spectrum. Toward a more accurate and effi…

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

Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization

Yang Li, Lvda Chen, Haonan Wang, Runzhong Wang, Junchi Yan
NeurIPS 2025poster

While diffusion models have shown promise for combinatorial optimization (CO), their inference-time scaling cost-efficiency remains relatively underexplored. Existing methods improve solution quality by increasing denoising steps, but the performance often becomes saturated quickly. This paper propo…

Cited by 0Source ↗Scholar ↗
2025

Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning

Runzhong Wang, Rui-Xi Wang, Mrunali Manjrekar, Connor W. Coley
ICML 2025poster

Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal integration of retrieval augmentation into molecular machine learni…

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

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

Yang Li, Jiale Ma, Wenzheng Pan, Runzhong Wang, Haoyu Geng, Nianzu Yang +1
ICLR 2025poster

Despite the rich works on machine learning (ML) for combinatorial optimization (CO), a unified, principled framework remains lacking. This study utilizes the Travelling Salesman Problem (TSP) as a major case study, with adaptations demonstrated for other CO problems, dissecting established mainstrea…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime

Haoyu Geng, Hang Ruan, Runzhong Wang, Yang Li, YANG WANG, Lei CHEN +1
NeurIPS 2024poster

Predictive combinatorial optimization, where the parameters of combinatorial optimization (CO) are unknown at the decision-making time, is the precise modeling of many real-world applications, including energy cost-aware scheduling and budget allocation on advertising. Tackling such a problem usuall…

Cited by 1Source ↗code ↗Scholar ↗
2024

Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search

Kevin Yu, Jihye Roh, Ziang Li, Wenhao Gao, Runzhong Wang, Connor W. Coley
NeurIPS 2024spotlight

Computer-aided synthesis planning (CASP) algorithms have demonstrated expert-level abilities in planning retrosynthetic routes to molecules of low to moderate complexity. However, current search methods assume the sufficiency of reaching arbitrary building blocks, failing to address the common real-…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2024

Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization

Yang Li, Jinpei Guo, Runzhong Wang, Hongyuan Zha, Junchi Yan
NeurIPS 2024poster

Diffusion models have recently advanced Combinatorial Optimization (CO) as a powerful backbone for neural solvers. However, their iterative sampling process requiring denoising across multiple noise levels incurs substantial overhead. We propose to learn direct mappings from different noise levels t…

Cited by 4Source ↗PDF ↗Scholar ↗
2024

LLMCO4MR: LLMs-aided Neural Combinatorial Optimization for Ancient Manuscript Restoration from Fragments with Case Studies on Dunhuang

Yuqing Zhang, Hangqi Li, Shengyu Zhang*, Runzhong Wang, Baoyi He, Huaiyong Dou +3
ECCV 2024poster

"Restoring ancient manuscripts fragments, such as those from Dunhuang, is crucial for preserving human historical culture. However, their worldwide dispersal and the shifts in cultural and historical contexts pose significant restoration challenges. Traditional archaeological efforts primarily focus…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Deep Learning of Partial Graph Matching via Differentiable Top-K

Runzhong Wang, Ziao Guo, Shaofei Jiang, Xiaokang Yang, Junchi Yan
CVPR 2023poster

Graph matching (GM) aims at discovering node matching between graphs, by maximizing the node- and edge-wise affinities between the matched elements. As an NP-hard problem, its challenge is further pronounced in the existence of outlier nodes in both graphs which is ubiquitous in practice, especially…

Cited by 13Source ↗PDF ↗Scholar ↗
2023

LinSATNet: The Positive Linear Satisfiability Neural Networks

Runzhong Wang, Yunhao Zhang, Ziao Guo, Tianyi Chen, Xiaokang Yang, Junchi Yan
ICML 2023poster

Encoding constraints into neural networks is attractive. This paper studies how to introduce the popular positive linear satisfiability to neural networks. We propose the first differentiable satisfiability layer based on an extension of the classic Sinkhorn algorithm for jointly encoding multiple s…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2023

MHSCNET: A Multimodal Hierarchical Shot-Aware Convolutional Network for Video Summarization

Wujiang Xu, Runzhong Wang, Xiaobo Guo, Shaoshuai Li, Qiongxu Ma, Yunan Zhao +3
ICASSP 2023accepted

Video summarization is an essential problem in signal processing, which intends to produce a concise summary of the original video. Existing video summarization approaches regard the task as a keyframe selection problem and generally construct the frame-wise representation by combining the long-rang…

Cited by 0Source ↗Scholar ↗
2023

ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs

Han Lu, Zenan Li, Runzhong Wang, Qibing Ren, Xijun Li, Mingxuan Yuan +3
ICLR 2023poster

Solving combinatorial optimization (CO) on graphs has been attracting increasing interests from the machine learning community whereby data-driven approaches were recently devised to go beyond traditional manually-designated algorithms. In this paper, we study the robustness of a combinatorial solve…

Cited by 19Source ↗PDF ↗Scholar ↗
2023

Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching

Chang Liu, Zetian Jiang, Runzhong Wang, Lingxiao Huang, Pinyan Lu, Junchi Yan
ICLR 2023poster

Graph matching (GM) has been a building block in various areas including computer vision and pattern recognition. Despite recent impressive progress, existing deep GM methods often have obvious difficulty in handling outliers, which are ubiquitous in practice. We propose a deep reinforcement learnin…

Cited by 11Source ↗PDF ↗Scholar ↗
2023

T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

Yang Li, Jinpei Guo, Runzhong Wang, Junchi Yan
NeurIPS 2023poster

Extensive experiments have gradually revealed the potential performance bottleneck of modeling Combinatorial Optimization (CO) solving as neural solution prediction tasks. The neural networks, in their pursuit of minimizing the average objective score across the distribution of historical problem in…

Cited by 75Source ↗PDF ↗Scholar ↗
2023

Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case

Runzhong Wang, Li Shen, Yiting Chen, Xiaokang Yang, Dacheng Tao, Junchi Yan
ICLR 2023poster

One-shot non-autoregressive neural networks, different from RL-based ones, have been actively adopted for solving combinatorial optimization (CO) problems, which can be trained by the objective score in a self-supervised manner. Such methods have shown their superiority in efficiency (e.g. by parall…

Cited by 18Source ↗PDF ↗Scholar ↗
2022

Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond

Qibing Ren, Qingquan Bao, Runzhong Wang, Junchi Yan
CVPR 2022poster

Despite the recent breakthrough of high accuracy deep graph matching (GM) over visual images, the robustness of deep GM models is rarely studied which yet has been revealed an important issue in modern deep nets, ranging from image recognition to graph learning tasks. We first show that an adversari…

Cited by 19PDF ↗code ↗Scholar ↗
2022

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning

Chang Liu, Chenfei Lou, Runzhong Wang, Alan Yuhan Xi, Li Shen, Junchi Yan
ICML 2022spotlight

Model fusion without accessing training data in machine learning has attracted increasing interest due to the practical resource-saving and data privacy issues. During the training process, the neural weights of each model can be randomly permuted, and we have to align the channels of each layer bef…

Cited by 75Source ↗PDF ↗code ↗Scholar ↗
2021

A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs

Runzhong Wang, Zhigang Hua, Gan Liu, Jiayi Zhang, Junchi Yan, Feng Qi +3
NeurIPS 2021poster

Combinatorial Optimization (CO) has been a long-standing challenging research topic featured by its NP-hard nature. Traditionally such problems are approximately solved with heuristic algorithms which are usually fast but may sacrifice the solution quality. Currently, machine learning for combinator…

Cited by 53Source ↗PDF ↗code ↗Scholar ↗
2021

Combinatorial Learning of Graph Edit Distance via Dynamic Embedding

Runzhong Wang, Tianqi Zhang, Tianshu Yu, Junchi Yan, Xiaokang Yang
CVPR 2021poster

Graph Edit Distance (GED) is a popular similarity measurement for pairwise graphs and it also refers to the recovery of the edit path from the source graph to the target graph. Traditional A* algorithm suffers scalability issues due to its exhaustive nature, whose search heuristics heavily rely on h…

Cited by 69PDF ↗code ↗Scholar ↗
2020

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning

Runzhong Wang, Junchi Yan, Xiaokang Yang
NeurIPS 2020poster

This paper considers the setting of jointly matching and clustering multiple graphs belonging to different groups, which naturally rises in many realistic problems. Both graph matching and clustering are challenging (NP-hard) and a joint solution is appealing due to the natural connection of the two…

Cited by 41Source ↗PDF ↗code ↗Scholar ↗
2020

Learning deep graph matching with channel-independent embedding and Hungarian attention

Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li
ICLR 2020poster

Graph matching aims to establishing node-wise correspondence between two graphs, which is a classic combinatorial problem and in general NP-complete. Until very recently, deep graph matching methods start to resort to deep networks to achieve unprecedented matching accuracy. Along this direction, th…

Cited by 118Source ↗Scholar ↗
2019

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

Hao-Shu Fang, Jianhua Sun, Runzhong Wang, Minghao Gou, Yong-Lu Li, Cewu Lu
ICCV 2019poster

Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g. bbox, point) in a…

Cited by 253PDF ↗code ↗Scholar ↗