papers

Publications (31)

stat.AP2025

Signed Rank Chart For Tied Observations: An Application of Deep Learning Models

Seyedeh Azadeh Fallah Mortezanejad, Ruochen Wang

Shewhart Control Charts (SCC)s are constructed under the assumption of normality and are widely recognized in statistical quality control by numerous researchers. Problems arise wh…

cs.CV2023

Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory

Justin Cui, Ruochen Wang, Si Si +1

Dataset Distillation is a newly emerging area that aims to distill large datasets into much smaller and highly informative synthetic ones to accelerate training and reduce storage.…

cs.LG2022

DC-BENCH: Dataset Condensation Benchmark

Justin Cui, Ruochen Wang, Si Si +1

Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets con…

cs.LG2024

On Discrete Prompt Optimization for Diffusion Models

Ruochen Wang, Ting Liu, Cho-Jui Hsieh +1

This paper introduces the first gradient-based framework for prompt optimization in text-to-image diffusion models. We formulate prompt engineering as a discrete optimization probl…

cs.CV2025

QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models

Kuei-Chun Kao, Hsu Tzu-Yin, Yunqi Hong +2

Recently, Multimodal Large Language Models (MLLMs) encounter two key issues in multi-image contexts: (1) a lack of fine-grained perception across disparate images, and (2) a dimini…

cs.AI2024

Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?

Kuei-Chun Kao, Ruochen Wang, Cho-Jui Hsieh

Large Language Models (LLMs) have demonstrated remarkable performance in solving math problems, a hallmark of human intelligence. Despite high success rates on current benchmarks;…

cs.SE2023

REVIS: An Error Visualization Tool for Rust

Ruochen Wang, Molly Maclaren, Michael Coblenz

Rust is a programming language that uses a concept of ownership to guarantee memory safety without the use of a garbage collector. However, some error messages related to ownership…

cs.CV2024

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise

Yuanhao Ban, Ruochen Wang, Tianyi Zhou +3

Diffusion models have achieved remarkable success in text-to-image generation tasks; however, the role of initial noise has been rarely explored. In this study, we identify specifi…

cs.CR2021

Optimizing Secure Decision Tree Inference Outsourcing

Yifeng Zheng, Cong Wang, Ruochen Wang +2

Outsourcing decision tree inference services to the cloud is highly beneficial, yet raises critical privacy concerns on the proprietary decision tree of the model provider and the…

cs.AI2025

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Hengguang Zhou, Xirui Li, Ruochen Wang +3

Recently DeepSeek R1 demonstrated how reinforcement learning with simple rule-based incentives can enable autonomous development of complex reasoning in large language models, char…

cs.LG2024

Mitigating Bias in Dataset Distillation

Justin Cui, Ruochen Wang, Yuanhao Xiong +1

Dataset Distillation has emerged as a technique for compressing large datasets into smaller synthetic counterparts, facilitating downstream training tasks. In this paper, we study…

cs.CV2022

Generalizing Few-Shot NAS with Gradient Matching

Shoukang Hu, Ruochen Wang, Lanqing Hong +3

Efficient performance estimation of architectures drawn from large search spaces is essential to Neural Architecture Search. One-Shot methods tackle this challenge by training one…

cs.AI2024

Large Language Models are Interpretable Learners

Ruochen Wang, Si Si, Felix Yu +3

The trade-off between expressiveness and interpretability remains a core challenge when building human-centric predictive models for classification and decision-making. While symbo…

cs.LG2022

Efficient Non-Parametric Optimizer Search for Diverse Tasks

Ruochen Wang, Yuanhao Xiong, Minhao Cheng +1

Efficient and automated design of optimizers plays a crucial role in full-stack AutoML systems. However, prior methods in optimizer search are often limited by their scalability, g…

cs.LG2022

FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning

Yuanhao Xiong, Ruochen Wang, Minhao Cheng +2

Federated learning~(FL) has recently attracted increasing attention from academia and industry, with the ultimate goal of achieving collaborative training under privacy and communi…

cs.CR2024

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Xirui Li, Ruochen Wang, Minhao Cheng +2

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. Howev…

cs.LG2021

RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving

Ruochen Wang, Xiangning Chen, Minhao Cheng +2

Predictor-based algorithms have achieved remarkable performance in the Neural Architecture Search (NAS) tasks. However, these methods suffer from high computation costs, as trainin…

cs.CV2024

Understanding the Impact of Negative Prompts: When and How Do They Take Effect?

Yuanhao Ban, Ruochen Wang, Tianyi Zhou +3

The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images.%, demonstrati…

cs.LG2025

Physics-Informed Neural Networks with Unknown Partial Differential Equations: an Application in Multivariate Time Series

Seyedeh Azadeh Fallah Mortezanejad, Ruochen Wang, Ali Mohammad-Djafari

A significant advancement in Neural Network (NN) research is the integration of domain-specific knowledge through custom loss functions. This approach addresses a crucial challenge…

cs.CV2025

Concepts or Skills? Rethinking Instruction Selection for Multi-modal Models

Andrew Bai, Justin Cui, Ruochen Wang +1

Vision-language instruction tuning achieves two main purposes: learning visual concepts and learning visual skills. In this paper, we found that vision-language benchmarks fall int…

stat.AP2024

Dependence control chart using maximum copula entropy

Seyedeh Azadeh Fallah Mortezanejad, Ruochen Wang, Gholamreza Mohtashami Borzadaran +1

Statistical quality control methods are noteworthy to producing standard production in manufacturing processes. In this regard, there are many classical manners to control the proc…

cs.LG2021

Rethinking Architecture Selection in Differentiable NAS

Ruochen Wang, Minhao Cheng, Xiangning Chen +2

Differentiable Neural Architecture Search is one of the most popular Neural Architecture Search (NAS) methods for its search efficiency and simplicity, accomplished by jointly opti…

cs.LG2025

Addressing Challenges in Time Series Forecasting: A Comprehensive Comparison of Machine Learning Techniques

Seyedeh Azadeh Fallah Mortezanejad, Ruochen Wang

The explosion of Time Series (TS) data, driven by advancements in technology, necessitates sophisticated analytical methods. Modern management systems increasingly rely on analyzin…

cs.AI2024

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

Ruochen Wang, Sohyun An, Minhao Cheng +3

Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively…

cs.NI2008

A Heuristic Scheduling Scheme in Multiuser OFDMA Networks

Zheng Sun, Zhiqiang He, Ruochen Wang +1

Conventional heterogeneous-traffic scheduling schemes utilize zero-delay constraint for real-time services, which aims to minimize the average packet delay among real-time users. H…

cs.LG2021

DrNAS: Dirichlet Neural Architecture Search

Xiangning Chen, Ruochen Wang, Minhao Cheng +2

This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing…

cs.AI2025

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models

Sohyun An, Ruochen Wang, Tianyi Zhou +1

While recent success of large reasoning models (LRMs) significantly advanced LLMs' reasoning capability by optimizing the final answer accuracy using reinforcement learning, they m…

physics.space-ph2026

A Machine-Learning-Based Global Thermospheric Density Forecasting Model

Ruochen Wang, Xiaoli Bai

Thermospheric mass density governs aerodynamic drag in low Earth orbit and is a primary source of uncertainty in orbit prediction and conjunction assessment, particularly during ge…

cs.CV2024

MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion

Sen Li, Ruochen Wang, Cho-Jui Hsieh +2

Existing text-to-image models still struggle to generate images of multiple objects, especially in handling their spatial positions, relative sizes, overlapping, and attribute bind…

stat.AP2023

Profile control chart based on maximum entropy

Seyedeh Azadeh Fallah Mortezanejad, Ruochen Wang, Gholamreza Mohtashami Borzadaran +2

Monitoring a process over time is so important in manufacturing processes to reduce the waste of money and time. Some charts as Shewhart, CUSUM, and EWMA are common to monitor a pr…

cs.CL2024

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Xirui Li, Hengguang Zhou, Ruochen Wang +3

Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstr…