Publications (74)
Electrical Control Grain Dimensionality with Multilevel Magnetic Anisotropy
Shengyao Li, Sabpreet Bhatti, Siew Lang Teo +11
In alignment with the increasing demand for larger storage capacity and longer data retention, electrical control of magnetic anisotropy has been a research focus in the realm of s…
DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
Xuan Shen, Yaohua Wang, Ming Lin +4
The rapid advances in Vision Transformer (ViT) refresh the state-of-the-art performances in various vision tasks, overshadowing the conventional CNN-based models. This ignites a fe…
Towards edge engineering of two-dimensional layered transition-metal dichalcogenides by chemical vapor deposition
Wei Fu, Mark John, Thathsara D. Maddumapatabandi +4
The manipulation of edge configurations and structures in atomically thin transition metal dichalcogenides (TMDs) for versatile functionalization has attracted intensive interest i…
Data-Driven Design-Test-Make-Analyze Paradigm for Inorganic Crystals: Ultrafast Synthesis of Ternary Oxides
Haiwen Dai, Matthew J. McDermott, Andy Paul Chen +19
Data-driven methodologies hold the promise of revolutionizing inorganic materials discovery, but they often face challenges due to discrepancies between theoretical predictions and…
Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving
Shivam Akhauri, Laura Zheng, Tom Goldstein +1
Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with u…
The Second Order Linear Model
Ming Lin, Shuang Qiu, Bin Hong +1
We study a fundamental class of regression models called the second order linear model (SLM). The SLM extends the linear model to high order functional space and has attracted cons…
Learning Accurate Entropy Model with Global Reference for Image Compression
Yichen Qian, Zhiyu Tan, Xiuyu Sun +5
In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyp…
Synaptic modulation of conductivity and magnetism in a CoPt-based electrochemical transistor
Shengyao Li, Bojun Miao, Xueyan Wang +5
Among various types of neuromorphic devices towards artificial intelligence, the electrochemical synaptic transistor emerges, in which the channel conductance is modulated by the i…
Which Factorization Machine Modeling is Better: A Theoretical Answer with Optimal Guarantee
Ming Lin, Shuang Qiu, Jieping Ye +5
Factorization machine (FM) is a popular machine learning model to capture the second order feature interactions. The optimal learning guarantee of FM and its generalized version is…
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
Xiyuan Wei, Ming Lin, Fanjiang Ye +4
This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or…
GeoLCR: Attention-based Geometric Loop Closure and Registration
Jing Liang, Sanghyun Son, Ming Lin +1
We present a novel algorithm specially designed for loop detection and registration that utilizes Lidar-based perception. Our approach to loop detection involves voxelizing point c…
Robust Gaussian Process Regression for Real-Time High Precision GPS Signal Enhancement
Ming Lin, Xiaomin Song, Qi Qian +4
Satellite-based positioning system such as GPS often suffers from large amount of noise that degrades the positioning accuracy dramatically especially in real-time applications. In…
DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation
Siqi Guo, Ming Lin, Tianbao Yang
Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Models (LLMs) to automatically conve…
Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition
Junyan Wang, Zhenhong Sun, Yichen Qian +5
3D convolution neural networks (CNNs) have been the prevailing option for video recognition. To capture the temporal information, 3D convolutions are computed along the sequences,…
Neural Architecture Design for GPU-Efficient Networks
Ming Lin, Hesen Chen, Xiuyu Sun +3
Many mission-critical systems are based on GPU for inference. It requires not only high recognition accuracy but also low latency in responding time. Although many studies are devo…
Resampling Strategy in Sequential Monte Carlo for Constrained Sampling Problems
Chencheng Cai, Rong Chen, Ming Lin
Sequential Monte Carlo (SMC) methods are a class of Monte Carlo methods that are used to obtain random samples of a high dimensional random variable in a sequential fashion. Many p…
PHORECAST: Enabling AI Understanding of Public Health Outreach Across Populations
Rifaa Qadri, Anh Nhat Nhu, Swati Ramnath +6
Understanding how diverse individuals and communities respond to persuasive messaging holds significant potential for advancing personalized and socially aware machine learning. Wh…
PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
Xuan Li, Yi-Ling Qiao, Peter Yichen Chen +4
Existing approaches to system identification (estimating the physical parameters of an object) from videos assume known object geometries. This precludes their applicability in a v…
Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis
Xiang Li, Aoxiao Zhong, Ming Lin +6
Tissue characterization has long been an important component of Computer Aided Diagnosis (CAD) systems for automatic lesion detection and further clinical planning. Motivated by th…
Aerial Diffusion: Text Guided Ground-to-Aerial View Translation from a Single Image using Diffusion Models
Divya Kothandaraman, Tianyi Zhou, Ming Lin +1
We present a novel method, Aerial Diffusion, for generating aerial views from a single ground-view image using text guidance. Aerial Diffusion leverages a pretrained text-image dif…
Long-short Term Motion Feature for Action Classification and Retrieval
Zhenzhong Lan, Xuanchong Li, Ming Lin +1
We propose a method for representing motion information for video classification and retrieval. We improve upon local descriptor based methods that have been among the most popular…
Fine-Grained AutoAugmentation for Multi-Label Classification
Ya Wang, Hesen Chen, Fangyi Zhang +4
Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better…
The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition
Zhenzhong Lan, Dezhong Yao, Ming Lin +2
Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents…
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities
Guihong Li, Duc Hoang, Kartikeya Bhardwaj +3
Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process. The key idea behind zero-…
Entroformer: A Transformer-based Entropy Model for Learned Image Compression
Yichen Qian, Ming Lin, Xiuyu Sun +2
One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and…
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition
Divya Kothandaraman, Ming Lin, Dinesh Manocha
We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras t…
Unveiling the emergent traits of chiral spin textures in magnetic multilayers
Xiaoye Chen, Ming Lin, Jian Feng Kong +7
Magnetic skyrmions are topologically wound nanoscale textures of spins whose ambient stability and electrical manipulation in multilayer films have led to an explosion of research…
Robust Finite Mixture Regression for Heterogeneous Targets
Jian Liang, Kun Chen, Ming Lin +2
Finite Mixture Regression (FMR) refers to the mixture modeling scheme which learns multiple regression models from the training data set. Each of them is in charge of a subset. FMR…
Research Opportunities and Visions for Smart and Pervasive Health
Elizabeth Mynatt, Gregory D. Hager, Santosh Kumar +4
Improving the health of the nation's population and increasing the capabilities of the US healthcare system to support diagnosis, treatment, and prevention of disease is a critical…
Knapsack Pruning with Inner Distillation
Yonathan Aflalo, Asaf Noy, Ming Lin +2
Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from -norm sparsification to Neural A…
Mesoscopic MCT theory resolves Giant Non-Gaussian Parameter and Flory's conjecture
Yikun Ren, Feixiang Xu, Ming Lin
Extending Prigogine's ideas to the interior of the system, we generalize mode-coupling theory from a microscopic to a mesoscopic formulation by incorporating the non-equilibrium ei…
HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
Divya Kothandaraman, Tianyi Zhou, Ming Lin +1
We present HawkI, for synthesizing aerial-view images from text and an exemplar image, without any additional multi-view or 3D information for finetuning or at inference. HawkI use…
WeMix: How to Better Utilize Data Augmentation
Yi Xu, Asaf Noy, Ming Lin +3
Data augmentation is a widely used training trick in deep learning to improve the network generalization ability. Despite many encouraging results, several recent studies did point…
Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
Ming Lin, Pichao Wang, Zhenhong Sun +5
Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking architectures. Building a high-quality accuracy predictor usually costs enormous computation.…
ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries
Zhou Chen, Xiao Wang, Yuanhong Liao +2
As the issue of global climate change becomes increasingly severe, the demand for research in climate science continues to grow. Natural language processing technologies, represent…
ViLA: Efficient Video-Language Alignment for Video Question Answering
Xijun Wang, Junbang Liang, Chun-Kai Wang +4
In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unifi…
Adaptive Conformal Guidance for Learning under Uncertainty
Rui Liu, Peng Gao, Yu Shen +2
Learning with guidance has proven effective across a wide range of machine learning systems. Guidance may, for example, come from annotated datasets in supervised learning, pseudo-…
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
Gang Li, Yan Chen, Ming Lin +1
Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these mo…
ICAR: Image-based Complementary Auto Reasoning
Xijun Wang, Anqi Liang, Junbang Liang +3
Scene-aware Complementary Item Retrieval (CIR) is a challenging task which requires to generate a set of compatible items across domains. Due to the subjectivity, it is difficult t…
Effects of virtual acoustics on dynamic auditory distance perception
Atul Rungta, Nicholas Rewkowski, Roberta Klatzky +2
Sound propagation encompasses various acoustic phenomena including reverberation. Current virtual acoustic methods, ranging from parametric filters to physically-accurate solvers,…
Making Vision Transformers Efficient from A Token Sparsification View
Shuning Chang, Pichao Wang, Ming Lin +4
The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to a…
Graphics4Science: Computer Graphics for Scientific Impacts
Peter Yichen Chen, Minghao Guo, Hanspeter Pfister +5
Computer graphics, often associated with films, games, and visual effects, has long been a powerful tool for addressing scientific challenges--from its origins in 3D visualization…
Nonconvex One-bit Single-label Multi-label Learning
Shuang Qiu, Tingjin Luo, Jieping Ye +1
We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels. We formulate this problem as a non-…
Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space
Yaohua Wang, Yaobin Zhang, Fangyi Zhang +4
Face clustering has attracted rising research interest recently to take advantage of massive amounts of face images on the web. State-of-the-art performance has been achieved by Gr…
KVT: k-NN Attention for Boosting Vision Transformers
Pichao Wang, Xue Wang, Fan Wang +4
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transforme…
Giant third-order nonlinear Hall effect in misfit layer compound (SnS)(NbS)
Shengyao Li, Xueyan Wang, Zherui Yang +11
Nonlinear Hall effect (NLHE) holds immense significance in recognizing the band geometry and its potential applications in current rectification. Recent discoveries have expanded t…
SHARE: Single-view Human Adversarial REconstruction
Shreelekha Revankar, Shijia Liao, Yu Shen +3
The accuracy of 3D Human Pose and Shape reconstruction (HPS) from an image is progressively improving. Yet, no known method is robust across all image distortion. To address issues…
GiraffeDet: A Heavy-Neck Paradigm for Object Detection
Yiqi Jiang, Zhiyu Tan, Junyan Wang +3
In conventional object detection frameworks, a backbone body inherited from image recognition models extracts deep latent features and then a neck module fuses these latent feature…
Search for Efficient Large Language Models
Xuan Shen, Pu Zhao, Yifan Gong +7
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and disti…
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing
Ming Lin, Jieping Ye
We develop an efficient alternating framework for learning a generalized version of Factorization Machine (gFM) on steaming data with provable guarantees. When the instances are sa…
Financial Models in Generative Art: Black-Scholes-Inspired Concept Blending in Text-to-Image Diffusion
Divya Kothandaraman, Ming Lin, Dinesh Manocha
We introduce a novel approach for concept blending in pretrained text-to-image diffusion models, aiming to generate images at the intersection of multiple text prompts. At each tim…
HandyPriors: Physically Consistent Perception of Hand-Object Interactions with Differentiable Priors
Shutong Zhang, Yi-Ling Qiao, Guanglei Zhu +6
Various heuristic objectives for modeling hand-object interaction have been proposed in past work. However, due to the lack of a cohesive framework, these objectives often possess…
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
Gang Li, Ming Lin, Tomer Galanti +2
The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning…
MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge Distillation
Rui Liu, Zikang Wang, Peng Gao +3
Autonomous systems have advanced significantly, but challenges persist in accident-prone environments where robust decision-making is crucial. A single vehicle's limited sensor ran…
Differentiable Analog Quantum Computing for Optimization and Control
Jiaqi Leng, Yuxiang Peng, Yi-Ling Qiao +2
We formulate the first differentiable analog quantum computing framework with a specific parameterization design at the analog signal (pulse) level to better exploit near-term quan…
CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems
Rui Liu, Yu Shen, Peng Gao +2
Multi-modal learning has emerged as a key technique for improving performance across domains such as autonomous driving, robotics, and reasoning. However, in certain scenarios, par…
Robust Graph Structure Learning via Multiple Statistical Tests
Yaohua Wang, FangYi Zhang, Ming Lin +3
Graph structure learning aims to learn connectivity in a graph from data. It is particularly important for many computer vision related tasks since no explicit graph structure is a…
Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning
Jidong Ge, Yuxiang Liu, Jie Gui +5
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations…
Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty
Rui Liu, Pratap Tokekar, Ming Lin
Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. E…
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
Xuan Shen, Peiyan Dong, Lei Lu +5
Large Language Models (LLMs) stand out for their impressive performance in intricate language modeling tasks. However, their demanding computational and memory needs pose obstacles…
WGICP: Differentiable Weighted GICP-Based Lidar Odometry
Sanghyun Son, Jing Liang, Ming Lin +1
We present a novel differentiable weighted generalized iterative closest point (WGICP) method applicable to general 3D point cloud data, including that from Lidar. Our method build…
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Peihao Wang, Shan Yang, Xijun Wang +8
Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability…
FAR: Fourier Aerial Video Recognition
Divya Kothandaraman, Tianrui Guan, Xijun Wang +3
We present an algorithm, Fourier Activity Recognition (FAR), for UAV video activity recognition. Our formulation uses a novel Fourier object disentanglement method to innately sepa…
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition
Zhenzhong Lan, Ming Lin, Xuanchong Li +2
Most state-of-the-art action feature extractors involve differential operators, which act as highpass filters and tend to attenuate low frequency action information. This attenuati…
Strategies for Searching Video Content with Text Queries or Video Examples
Shoou-I Yu, Yi Yang, Zhongwen Xu +13
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. Howev…
HART: Human Aligned Reconstruction Transformer
Xiyi Chen, Shaofei Wang, Marko Mihajlovic +3
We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh…
Handcrafted Local Features are Convolutional Neural Networks
Zhenzhong Lan, Shoou-I Yu, Ming Lin +2
Image and video classification research has made great progress through the development of handcrafted local features and learning based features. These two architectures were prop…
CharCom: Composable Identity Control for Multi-Character Story Illustration
Zhongsheng Wang, Ming Lin, Zhedong Lin +3
Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and param…
Time-Aware World Model for Adaptive Prediction and Control
Anh N. Nhu, Sanghyun Son, Ming Lin
In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Ît, and…
MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection
Zhenhong Sun, Ming Lin, Xiuyu Sun +3
In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architec…
Merino: Entropy-driven Design for Generative Language Models on IoT Devices
Youpeng Zhao, Ming Lin, Huadong Tang +2
Generative Large Language Models (LLMs) stand as a revolutionary advancement in the modern era of artificial intelligence (AI). However, scaling down LLMs for resource-constrained…
Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation
Shivam Akhauri, Laura Zheng, Ming Lin
Simulation data can be utilized to extend real-world driving data in order to cover edge cases, such as vehicle accidents. The importance of handling edge cases can be observed in…
Lookahead Strategies for Sequential Monte Carlo
Ming Lin, Rong Chen, Jun S. Liu
Based on the principles of importance sampling and resampling, sequential Monte Carlo (SMC) encompasses a large set of powerful techniques dealing with complex stochastic dynamic s…
Non-Equilibrium Thermodynamics Framework to Address the Glass Transition
Yikun Ren, Feixiang Xu, Ming Lin
When the center of fluctuations, i.e., the nonequilibrium eigenphase, undergoes transformation, there emerge critical parameters that demonstrate insensitivity to fluctuation pertu…