Publications (45)
DiffTune: Hyperparameter-Free Auto-Tuning using Auto-Differentiation
Sheng Cheng, Lin Song, Minkyung Kim +2
Controller tuning is a vital step to ensure the controller delivers its designed performance. DiffTune has been proposed as an automatic tuning method that unrolls the dynamical sy…
An Optimality Gap Test for a Semidefinite Relaxation of a Quadratic Program with Two Quadratic Constraints
Sheng Cheng, Nuno C. Martins
We propose a necessary and sufficient test to determine whether a solution for a general quadratic program with two quadratic constraints (QC2QP) can be computed from that of a spe…
UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Driving
Zhexiao Xiong, Xin Ye, Burhan Yaman +5
World models have become central to autonomous driving, where accurate scene understanding and future prediction are crucial for safe control. Recent work has explored using vision…
SecCoder: Towards Generalizable and Robust Secure Code Generation
Boyu Zhang, Tianyu Du, Junkai Tong +5
After large models (LMs) have gained widespread acceptance in code-related tasks, their superior generative capacity has greatly promoted the application of the code LM. Neverthele…
Self-Supervised Learning for Building Robust Pediatric Chest X-ray Classification Models
Sheng Cheng, Zbigniew A. Starosolski, Devika Subramanian
Recent advancements in deep learning for Medical Artificial Intelligence have demonstrated that models can match the diagnostic performance of clinical experts in adult chest X-ray…
EROICA: Online Performance Troubleshooting for Large-scale Model Training
Yu Guan, Zhiyu Yin, Haoyu Chen +11
Troubleshooting performance problems of large model training (LMT) is immensely challenging, due to unprecedented scales of modern GPU clusters, the complexity of software-hardware…
Tool-Planner: Task Planning with Clusters across Multiple Tools
Yanming Liu, Xinyue Peng, Jiannan Cao +6
Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the p…
SSR-GNNs: Stroke-based Sketch Representation with Graph Neural Networks
Sheng Cheng, Yi Ren, Yezhou Yang
This paper follows cognitive studies to investigate a graph representation for sketches, where the information of strokes, i.e., parts of a sketch, are encoded on vertices and info…
Latent Space Energy-based Neural ODEs
Sheng Cheng, Deqian Kong, Jianwen Xie +3
This paper introduces novel deep dynamical models designed to represent continuous-time sequences. Our approach employs a neural emission model to generate each data point in the t…
ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations
Maitreya Patel, Changhoon Kim, Sheng Cheng +2
Text-to-image (T2I) diffusion models, notably the unCLIP models (e.g., DALL-E-2), achieve state-of-the-art (SOTA) performance on various compositional T2I benchmarks, at the cost o…
Adversarial Bayesian Augmentation for Single-Source Domain Generalization
Sheng Cheng, Tejas Gokhale, Yezhou Yang
Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exis…
An Optimization-Based Planner with B-spline Parameterized Continuous-Time Reference Signals
Chuyuan Tao, Sheng Cheng, Yang Zhao +2
For the cascaded planning and control modules implemented for robot navigation, the frequency gap between the planner and controller has received limited attention. In this study,…
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
Maitreya Patel, Abhiram Kusumba, Sheng Cheng +4
Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the train…
Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
Sheng Cheng, Maitreya Patel, Yezhou Yang
Despite advancements in text-to-image models, generating images that precisely align with textual descriptions remains challenging due to misalignment in training data. In this pap…
Dimensional Control of Octahedral Tilt in SrRuO3 via Infinite-layered Oxides
Shan Lin, Qinghua Zhang, Xiahan Sang +16
Manipulation of octahedral distortion at atomic length scale is an effective means to tune the physical ground states of functional oxides. Previous work demonstrates that epitaxia…
Simultaneous Spatial and Temporal Assignment for Fast UAV Trajectory Optimization using Bilevel Optimization
Qianzhong Chen, Sheng Cheng, Naira Hovakimyan
In this paper, we propose a framework for fast trajectory planning for unmanned aerial vehicles (UAVs). Our framework is reformulated from an existing bilevel optimization, in whic…
Smooth Reference Command Generation and Control for Transition Flight of VTOL Aircraft Using Time-Varying Optimization
Jinrae Kim, John L. Bullock, Sheng Cheng +1
Vertical take-off and landing (VTOL) aircraft pose a challenge in generating reference commands during transition flight. While sparsity between hover and cruise flight modes can b…
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Yanming Liu, Xinyue Peng, Jiannan Cao +6
Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy context…
LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Models
Yijie Zhi, Yayu Cao, Jianhua Dai +5
Loop transformations are semantics-preserving optimization techniques, widely used to maximize objectives such as parallelism. Despite decades of research, applying the optimal com…
A New Super-Resolution Measurement of Perceptual Quality and Fidelity
Sheng Cheng
Super-resolution results are usually measured by full-reference image quality metrics or human rating scores. However, these evaluation methods are general image quality measuremen…
A Simulation Evaluation Suite for Robust Adaptive Quadcopter Control
Dingqi Zhang, Ran Tao, Sheng Cheng +2
Robust adaptive control methods are essential for maintaining quadcopter performance under external disturbances and model uncertainties. However, fragmented evaluations across tas…
DaI: Decrypt and Infer the Quality of Real-Time Video Streaming
Sheng Cheng
Inferring the quality of network services is the vital basis of optimization for network operators. However, prevailing real-time video streaming applications adopt encryption for…
Adaptive Augmentation for Geometric Tracking Control of Quadrotors
Zhuohuan Wu, Sheng Cheng, Kasey A. Ackerman +4
This paper introduces an adaptive control augmentation for geometric tracking control of quadrotors. In the proposed design, the augmentation handle…
Proto-MPC: An Encoder-Prototype-Decoder Approach for Quadrotor Control in Challenging Winds
Yuliang Gu, Sheng Cheng, Naira Hovakimyan
Quadrotors are increasingly used in the evolving field of aerial robotics for their agility and mechanical simplicity. However, inherent uncertainties, such as aerodynamic effects…
MUSE: Multimodal Uncertainty Quantification of State Estimation
Minkyung Kim, Henry Che, Bhargav Chandaka +6
Accurate visual state estimation has been a central topic in robotics with a wide range of applications in robot navigation, autonomous driving, and autonomous flight. Recent advan…
Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks
Yutian Pang, Sheng Cheng, Jueming Hu +1
To evaluate the robustness gain of Bayesian neural networks on image classification tasks, we perform input perturbations, and adversarial attacks to the state-of-the-art Bayesian…
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
Changhoon Kim, Kyle Min, Maitreya Patel +2
The rapid advancement of generative models, facilitating the creation of hyper-realistic images from textual descriptions, has concurrently escalated critical societal concerns suc…
Data-Driven Learning of 3-Point Correlation Functions as Microstructure Representations
Sheng Cheng, Yang Jiao, Yi Ren
This paper considers the open challenge of identifying complete, concise, and explainable quantitative microstructure representations for disordered heterogeneous material systems.…
DiffTune: Auto-Tuning through Auto-Differentiation
Sheng Cheng, Minkyung Kim, Lin Song +4
The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and…
Verification of Adaptive Control using Verse Library: A Case Study of Quadrotors
Lin Song, Yangge Li, Sheng Cheng +3
adaptive control (AC) is a control design technique that can handle a broad class of system uncertainties and provide transient performance guarantees. In this work-in-p…
Geometric Tracking Control of Omnidirectional Multirotors for Aggressive Maneuvers
Hyungyu Lee, Sheng Cheng, Zhuohuan Wu +3
An omnidirectional multirotor has the maneuverability of decoupled translational and rotational motions, superseding the traditional multirotors' motion capability. Such maneuverab…
Optimal guidance and estimation of a 2D diffusion-advection process by a team of mobile sensors
Sheng Cheng, Derek A. Paley
This paper describes an optimization framework to design guidance for a possibly heterogeneous team of multiple mobile sensors to estimate a spatiotemporal process modeled by a 2D…
Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control
Sheng Cheng, Ran Tao, Yuliang Gu +3
This paper presents the Task-Parameter Nexus (TPN), a learning-based approach for online determination of the (near-)optimal control parameters of model-based controllers (MBCs) fo…
DiffTune-MPC: Closed-Loop Learning for Model Predictive Control
Ran Tao, Sheng Cheng, Xiaofeng Wang +2
Model predictive control (MPC) has been applied to many platforms in robotics and autonomous systems for its capability to predict a system's future behavior while incorporating co…
Consistent User-Traffic Allocation and Load Balancing in Mobile Edge Caching
Lemei Huang, Sheng Cheng, Yu Guan +2
Cache-equipped Base-Stations (CBSs) is an attractive alternative to offload the rapidly growing backhaul traffic in a mobile network. New 5G technology and dense femtocell enable o…
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
Yanming Liu, Xinyue Peng, Yuwei Zhang +10
Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significan…
Synergistic Perception and Control Simplex for Verifiable Safe Vertical Landing
Ayoosh Bansal, Yang Zhao, James Zhu +6
Perception, Planning, and Control form the essential components of autonomy in advanced air mobility. This work advances the holistic integration of these components to enhance the…
Real-Time Linear MPC for Quadrotors on SE(3): An Analytical Koopman-based Realization
Santosh M. Rajkumar, Chengyu Yang, Yuliang Gu +3
This letter presents an analytical linear parameter-varying (LPV) representation of quadrotor dynamics utilizing Koopman theory, facilitating computationally efficient linear model…
Quad: Adaptive Augmentation of Geometric Control for Agile Quadrotors with Performance Guarantees
Zhuohuan Wu, Sheng Cheng, Pan Zhao +6
Quadrotors that can operate predictably in the presence of imperfect model knowledge and external disturbances are crucial in safety-critical applications. We present L1Quad, a con…
BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance
Xin Ye, Burhaneddin Yaman, Sheng Cheng +3
Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitatio…
Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter
Jianhui Zhang, Sheng Cheng, Qirui Sun +7
In this work, we present Patch-Adapter, an effective framework for high-resolution text-guided image inpainting. Unlike existing methods limited to lower resolutions, our approach…
Optimal control of a 2D diffusion-advection process with a team of mobile actuators under jointly optimal guidance
Sheng Cheng, Derek A. Paley
This paper describes an optimization framework to control a distributed parameter system (DPS) using a team of mobile actuators. The framework simultaneously seeks optimal control…
DeepRS: Deep-learning Based Network-Adaptive FEC for Real-Time Video Communications
Sheng Cheng, Han Hu, Xinggong Zhang +1
This work proposes an innovative approach to handle packet loss in real-time video streaming scenarios in a more sophisticated way -- Predicting packet loss pattern on time field b…
Autotuning Bipedal Locomotion MPC with GRFM-Net for Efficient Sim-to-Real Transfer
Qianzhong Chen, Junheng Li, Sheng Cheng +2
Bipedal locomotion control is essential for humanoid robots to navigate complex, human-centric environments. While optimization-based control designs are popular for integrating so…
DiffCoTune: Differentiable Co-Tuning for Cross-domain Robot Control
Lokesh Krishna, Sheng Cheng, Junheng Li +2
The deployment of robot controllers is hindered by modeling discrepancies due to necessary simplifications for computational tractability or inaccuracies in data-generating simulat…