arXiv subjects

Huidong Liu

Publications and source records attributed to Huidong Liu.

17 recordsLinked to original sources

arXiv2026

AgilePE: Autonomous UAV Pursuit-Evasion via Self-Play Reinforcement Learning

Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynamics and continuously changing opponent behaviors. Traditional rule-based or differential-game approaches often struggle with high-dimensional aerial interactions and agile maneuvering. We present AgilePE, a complete system for autonomous UAV pursuit-evasion via self-play reinforcement learning. AgilePE integrates agile low-level control, competitive policy optimization, and sim-to-real deployment in a unified framework. The policy directly maps onboard state observations to Collective Thrust and Body Rates (CTBR) commands, enabling end-to-end agile maneuvering without intermediate trajectory planners or waypoint controllers. For training, we use competitive self-play with Prioritized Fictitious Self-Play (PFSP) and a diversified opponent pool, enabling agents to improve against historical policies while stabilizing optimization and reducing policy oscillation. This process leads to the emergence of sophisticated pursuit and evasion strategies. For real-world deployment, we develop a hardware-aligned simulation pipeline that models actuator-response dynamics, communication latency, and domain randomization. The learned policies transfer zero-shot to real quadrotors without task-specific tuning. Real-world experiments reproduce pursuit-evasion tactics observed in simulation, including rapid dodging and flanking, and demonstrate interactive two-agent zero-shot deployment.

cs.RO↗

arXiv2026

Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification

Mechanical ventilation (MV) is a life-saving intervention for patients with acute respiratory failure (ARF) in the ICU. However, inappropriate ventilator settings could cause ventilator-induced lung injury (VILI). Also, clinicians workload is shown to be directly linked to patient outcomes. Hence, MV should be personalized and automated to improve patient outcomes. Previous attempts to incorporate personalization and automation in MV include traditional supervised learning and offline reinforcement learning (RL) approaches, which often neglect temporal dependencies and rely excessively on mortality-based rewards. As a result, early stage physiological deterioration and the risk of VILI are not adequately captured. To address these limitations, we propose Transformer-based Conservative Q-Learning (T-CQL), a novel offline RL framework that integrates a Transformer encoder for effective temporal modeling of patient dynamics, conservative adaptive regularization based on uncertainty quantification to ensure safety, and consistency regularization for robust decision-making. We build a clinically informed reward function that incorporates indicators of VILI and a score for severity of patients illness. Also, previous work predominantly uses Fitted Q-Evaluation (FQE) for RL policy evaluation on static offline data, which is less responsive to dynamic environmental changes and susceptible to distribution shifts. To overcome these evaluation limitations, interactive digital twins of ARF patients were used for online "at the bedside" evaluation. Our results demonstrate that T-CQL consistently outperforms existing state-of-the-art offline RL methodologies, providing safer and more effective ventilatory adjustments. Our framework demonstrates the potential of Transformer-based models combined with conservative RL strategies as a decision support tool in critical care.

cs.LG↗

arXiv2025

Heteroscedastic Bayesian Optimization-Based Dynamic PID Tuning for Accurate and Robust UAV Trajectory Tracking

Unmanned Aerial Vehicles (UAVs) play an important role in various applications, where precise trajectory tracking is crucial. However, conventional control algorithms for trajectory tracking often exhibit limited performance due to the underactuated, nonlinear, and highly coupled dynamics of quadrotor systems. To address these challenges, we propose HBO-PID, a novel control algorithm that integrates the Heteroscedastic Bayesian Optimization (HBO) framework with the classical PID controller to achieve accurate and robust trajectory tracking. By explicitly modeling input-dependent noise variance, the proposed method can better adapt to dynamic and complex environments, and therefore improve the accuracy and robustness of trajectory tracking. To accelerate the convergence of optimization, we adopt a two-stage optimization strategy that allow us to more efficiently find the optimal controller parameters. Through experiments in both simulation and real-world scenarios, we demonstrate that the proposed method significantly outperforms state-of-the-art (SOTA) methods. Compared to SOTA methods, it improves the position accuracy by 24.7% to 42.9%, and the angular accuracy by 40.9% to 78.4%.

cs.RO↗

arXiv2025

AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport

Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to couple noise and data during FGM training has been shown to improve the straightness of flow trajectories, enabling more effective inference. However, existing OT-based methods estimate the OT plan using (mini-)batches of sampled noise and data points, which limits their scalability to large and high-dimensional datasets in FGMs. This paper introduces AlignFlow, a novel approach that leverages Semi-Discrete Optimal Transport (SDOT) to enhance the training of FGMs by establishing an explicit, optimal alignment between noise distribution and data points with guaranteed convergence. SDOT computes a transport map by partitioning the noise space into Laguerre cells, each mapped to a corresponding data point. During FGM training, i.i.d. noise samples are paired with data points via the SDOT map. AlignFlow scales well to large datasets and model architectures with negligible computational overhead. Experimental results show that AlignFlow improves the performance of a wide range of state-of-the-art FGM algorithms and can be integrated as a plug-and-play component. Code is available at: https://github.com/konglk1203/AlignFlow.

cs.LG↗

arXiv2025

Temporal-Consistent Video Restoration with Pre-trained Diffusion Models

Video restoration (VR) aims to recover high-quality videos from degraded ones. Although recent zero-shot VR methods using pre-trained diffusion models (DMs) show good promise, they suffer from approximation errors during reverse diffusion and insufficient temporal consistency. Moreover, dealing with 3D video data, VR is inherently computationally intensive. In this paper, we advocate viewing the reverse process in DMs as a function and present a novel Maximum a Posterior (MAP) framework that directly parameterizes video frames in the seed space of DMs, eliminating approximation errors. We also introduce strategies to promote bilevel temporal consistency: semantic consistency by leveraging clustering structures in the seed space, and pixel-level consistency by progressive warping with optical flow refinements. Extensive experiments on multiple virtual reality tasks demonstrate superior visual quality and temporal consistency achieved by our method compared to the state-of-the-art.

cs.CV↗

arXiv2023

Hydrogel modified evaporation interface for highly stable membrane distillation

Surface effect of low-surface-tension contaminants accumulating at the evaporation surface can easily induce membrane wetting in the application of membrane distillation, especially in hypersaline scenarios. In this work, we propose a novel strategy to eliminate the surface effect and redistribute contaminants at the evaporation interface with simply incorporating a layer of hydrogel. The as-fabricated composite membrane exhibits remarkable stability, even when exposed to extreme conditions, such as a salt concentration of 5M and surfactant concentration of 8 mM. The breakthrough pressure of the membrane is as high as 20 bars in the presence of surfactants, surpassing commercial hydrophobic membranes by one to two magnitudes. Combined study of density functional theory and molecular dynamics simulations reveals the important role of hydrogel-surfactant interaction in suppressing the surface effect. As a proof of concept, we also demonstrate the stable performance of the membrane in processing synthetic wastewater containing surfactants of 144 mg L-1, mineral oils of 1g L-1 and NaCl of 192 g L-1, showing potential of the membrane in addressing challenges of hypersaline water treatment and zero liquid discharge processes.

physics.chem-ph↗

arXiv2023

Hierarchical Conditional Semi-Paired Image-to-Image Translation For Multi-Task Image Defect Correction On Shopping Websites

On shopping websites, product images of low quality negatively affect customer experience. Although there are plenty of work in detecting images with different defects, few efforts have been dedicated to correct those defects at scale. A major challenge is that there are thousands of product types and each has specific defects, therefore building defect specific models is unscalable. In this paper, we propose a unified Image-to-Image (I2I) translation model to correct multiple defects across different product types. Our model leverages an attention mechanism to hierarchically incorporate high-level defect groups and specific defect types to guide the network to focus on defect-related image regions. Evaluated on eight public datasets, our model reduces the Frechet Inception Distance (FID) by 24.6% in average compared with MoNCE, the state-of-the-art I2I method. Unlike public data, another practical challenge on shopping websites is that some paired images are of low quality. Therefore we design our model to be semi-paired by combining the L1 loss of paired data with the cycle loss of unpaired data. Tested on a shopping website dataset to correct three image defects, our model reduces (FID) by 63.2% in average compared with WS-I2I, the state-of-the art semi-paired I2I method.

cs.CV↗

arXiv2023

Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual information to infer masked image regions. We believe that this context aggregation ability is particularly essential to the medical image domain where each anatomical structure is functionally and mechanically connected to other structures and regions. Because there is no ImageNet-scale medical image dataset for pre-training, we investigate a self pre-training paradigm with MAE for medical image analysis tasks. Our method pre-trains a ViT on the training set of the target data instead of another dataset. Thus, self pre-training can benefit more scenarios where pre-training data is hard to acquire. Our experimental results show that MAE self pre-training markedly improves diverse medical image tasks including chest X-ray disease classification, abdominal CT multi-organ segmentation, and MRI brain tumor segmentation. Code is available at https://github.com/cvlab-stonybrook/SelfMedMAE

eess.IV↗

arXiv2023

Token Sparsification for Faster Medical Image Segmentation

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens. To this end, we reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline. We first empirically show that naively applying existing approaches from classification token pruning and masked image modeling (MIM) leads to failure and inefficient training caused by inappropriate sampling algorithms and the low quality of the restored dense features. In this paper, we propose Soft-topK Token Pruning (STP) and Multi-layer Token Assembly (MTA) to address these problems. In sparse encoding, STP predicts token importance scores with a lightweight sub-network and samples the topK tokens. The intractable topK gradients are approximated through a continuous perturbed score distribution. In token completion, MTA restores a full token sequence by assembling both sparse output tokens and pruned multi-layer intermediate ones. The last dense decoding stage is compatible with existing segmentation decoders, e.g., UNETR. Experiments show SCD pipelines equipped with STP and MTA are much faster than baselines without token pruning in both training (up to 120% higher throughput and inference up to 60.6% higher throughput) while maintaining segmentation quality.

cs.CV↗

arXiv2022

Lung Swapping Autoencoder: Learning a Disentangled Structure-texture Representation of Chest Radiographs

Well-labeled datasets of chest radiographs (CXRs) are difficult to acquire due to the high cost of annotation. Thus, it is desirable to learn a robust and transferable representation in an unsupervised manner to benefit tasks that lack labeled data. Unlike natural images, medical images have their own domain prior; e.g., we observe that many pulmonary diseases, such as the COVID-19, manifest as changes in the lung tissue texture rather than the anatomical structure. Therefore, we hypothesize that studying only the texture without the influence of structure variations would be advantageous for downstream prognostic and predictive modeling tasks. In this paper, we propose a generative framework, the Lung Swapping Autoencoder (LSAE), that learns factorized representations of a CXR to disentangle the texture factor from the structure factor. Specifically, by adversarial training, the LSAE is optimized to generate a hybrid image that preserves the lung shape in one image but inherits the lung texture of another. To demonstrate the effectiveness of the disentangled texture representation, we evaluate the texture encoder $Enc^t$ in LSAE on ChestX-ray14 (N=112,120), and our own multi-institutional COVID-19 outcome prediction dataset, COVOC (N=340 (Subset-1) + 53 (Subset-2)). On both datasets, we reach or surpass the state-of-the-art by finetuning $Enc^t$ in LSAE that is 77% smaller than a baseline Inception v3. Additionally, in semi-and-self supervised settings with a similar model budget, $Enc^t$ in LSAE is also competitive with the state-of-the-art MoCo. By "re-mixing" the texture and shape factors, we generate meaningful hybrid images that can augment the training set. This data augmentation method can further improve COVOC prediction performance. The improvement is consistent even when we directly evaluate the Subset-1 trained model on Subset-2 without any fine-tuning.

eess.IV↗

arXiv2021

CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification

Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and recommendation. In this paper, we propose the Cross-Modality Attention Contrastive Language-Image Pre-training (CMA-CLIP), a new framework which unifies two types of cross-modality attentions, sequence-wise attention and modality-wise attention, to effectively fuse information from image and text pairs. The sequence-wise attention enables the framework to capture the fine-grained relationship between image patches and text tokens, while the modality-wise attention weighs each modality by its relevance to the downstream tasks. In addition, by adding task specific modality-wise attentions and multilayer perceptrons, our proposed framework is capable of performing multi-task classification with multi-modalities. We conduct experiments on a Major Retail Website Product Attribute (MRWPA) dataset and two public datasets, Food101 and Fashion-Gen. The results show that CMA-CLIP outperforms the pre-trained and fine-tuned CLIP by an average of 11.9% in recall at the same level of precision on the MRWPA dataset for multi-task classification. It also surpasses the state-of-the-art method on Fashion-Gen Dataset by 5.5% in accuracy and achieves competitive performance on Food101 Dataset. Through detailed ablation studies, we further demonstrate the effectiveness of both cross-modality attention modules and our method's robustness against noise in image and text inputs, which is a common challenge in practice.

cs.CV↗

arXiv2021

AlCrO protected textured stainless steel surface for high temperature solar selective absorber applications

The diffusion of substrate material into absorbing layer and oxidation of metal substrate or cermet metal nanoparticles at high temperatures are known as inevitable problems of the solar selective absorbers. In this study, we consider the use of textured stainless steel (SS) surface coated with a protective AlCr oxide layer as a high temperature solar selective absorber. The textured SS surface was prepared by ion etching techniques and AlCr oxide protective layer was deposited by RF magnetron sputtering. The absorptivity and emissivity of the as-prepared absorbers were 0.86-0.92 and 0.151-0.168, respectively. In order to evaluate the thermal stability, the absorbers were annealed at 600-800 C for different time in ambient atmosphere. Absorbers demonstrated a red shift of the onset of the reflectivity at all annealing temperatures. The high activation energy of 315 kJ/mol was calculated. The service lifetime of the absorbers at 500 C was estimated to be about 100 years and at 700 and 800 C the absorbers were stable about 50 and 1 hours, respectively. A detailed examination of the annealed absorber surface revealed growth of surface Mn3O4 nanocrystals, which resulted in observed change of the reflectance spectra, while the textured surface morphology had no significant change. The results show that the protective textured surface has much higher thermal stability in air than iron based cermet absorbers.

physics.chem-ph↗

arXiv2021

Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach

Recently, Generative Adversarial Networks (GANs) have demonstrated their potential in federated learning, i.e., learning a centralized model from data privately hosted by multiple sites. A federatedGAN jointly trains a centralized generator and multiple private discriminators hosted at different sites. A major theoretical challenge for the federated GAN is the heterogeneity of the local data distributions. Traditional approaches cannot guarantee to learn the target distribution, which isa mixture of the highly different local distributions. This paper tackles this theoretical challenge, and for the first time, provides a provably correct framework for federated GAN. We propose a new approach called Universal Aggregation, which simulates a centralized discriminator via carefully aggregating the mixture of all private discriminators. We prove that a generator trained with this simulated centralized discriminator can learn the desired target distribution. Through synthetic and real datasets, we show that our method can learn the mixture of largely different distributions where existing federated GAN methods fail.

cs.LG↗

arXiv2020

Distribution Matching for Crowd Counting

In crowd counting, each training image contains multiple people, where each person is annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood of every pixel given the annotated point. In this paper, we show that imposing Gaussians to annotations hurts generalization performance. Instead, we propose to use Distribution Matching for crowd COUNTing (DM-Count). In DM-Count, we use Optimal Transport (OT) to measure the similarity between the normalized predicted density map and the normalized ground truth density map. To stabilize OT computation, we include a Total Variation loss in our model. We show that the generalization error bound of DM-Count is tighter than that of the Gaussian smoothed methods. In terms of Mean Absolute Error, DM-Count outperforms the previous state-of-the-art methods by a large margin on two large-scale counting datasets, UCF-QNRF and NWPU, and achieves the state-of-the-art results on the ShanghaiTech and UCF-CC50 datasets. DM-Count reduced the error of the state-of-the-art published result by approximately 16%. Code is available at https://github.com/cvlab-stonybrook/DM-Count.

cs.CV↗

arXiv2018

Thermal-driven Flow inside Graphene Channels for Water Desalination

A novel concept of membrane process in thermal-driven system is proposed for water desalination. By means of molecular dynamics simulations, we show fast water transport through graphene galleries at a temperature gradient. Water molecules are driven to migrate through nanometer-wide graphene channels from cold reservoir to hot reservoir by the effect of thermal creep flow. Reducing the interlayer spacing to 6.5 Å, an abrupt escalation occurs in water permeation between angstrom-distance graphene slabs. The change from disordered bulklike water to quasi-square structure have been found under this extremely confined condition. This leads to a transition to subcontinuum transport. Water molecules perform collective diffusion behaviors inside graphene channels. The special transport processes with structure change convert thermal energy into motion without dissipation, resulting in unexpected high water permeability. The thermal-driven system reaches maximum flowrate at temperature variance of 80 K, corresponding to the quantity at pressure difference up to 10^5 bar in commercial reverse osmosis processes and 230 bar in pressure-driven slip flow. Our results also reveal the movement of saline ions influenced by thermophoretic effect, which complement the geometry limitation at greater layer spacing, enhancing the blockage of ions. This finding aims to provide an innovational idea of developing a high-efficiency desalination technology able to utilize various forms of energy.

cond-mat.soft↗

arXiv2018

Latent Space Optimal Transport for Generative Models

Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which can be important for datasets such as facial images. A GAN can transform a simple distribution to a latent-space data distribution and thus preserve the manifold structure, but optimizing a GAN involves solving a Min-Max optimization problem, which is difficult and not well understood so far. Therefore, we propose a GAN-like method to transform a simple distribution to a data distribution in the latent space by solving only a minimization problem. This minimization problem comes from training a discriminator between a simple distribution and a latent-space data distribution. Then, we can explicitly formulate an Optimal Transport (OT) problem that computes the desired mapping between the two distributions. This means that we can transform a distribution without solving the difficult Min-Max optimization problem. Experimental results on an eight-Gaussian dataset show that the proposed OT can handle multi-cluster distributions. Results on the MNIST and the CelebA datasets validate the effectiveness of the proposed method.

cs.LG↗

arXiv2018

Implementation of Stochastic Quasi-Newton's Method in PyTorch

In this paper, we implement the Stochastic Damped LBFGS (SdLBFGS) for stochastic non-convex optimization. We make two important modifications to the original SdLBFGS algorithm. First, by initializing the Hessian at each step using an identity matrix, the algorithm converges better than original algorithm. Second, by performing direction normalization we could gain stable optimization procedure without line search. Experiments on minimizing a 2D non-convex function shows that our improved algorithm converges better than original algorithm, and experiments on the CIFAR10 and MNIST datasets show that our improved algorithm works stably and gives comparable or even better testing accuracies than first order optimizers SGD, Adagrad, and second order optimizers LBFGS in PyTorch.

cs.LG↗