Publications (63)
Orthogonal Weight Modification Enhances Learning Scalability and Convergence Efficiency without Gradient Backpropagation
Guoqing Ma, Shan Yu
Recognizing the substantial computational cost of backpropagation (BP), non-BP methods have emerged as attractive alternatives for efficient learning on emerging neuromorphic syste…
Flexible Tool Selection through Low-dimensional Attribute Alignment of Vision and Language
Guangfu Hao, Haojie Wen, Liangxuan Guo +3
Flexible tool selection reflects a complex cognitive ability that distinguishes humans from other species, yet computational models that capture this ability remain underdeveloped.…
EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks
Lubin Meng, Jian Huang, Zhigang Zeng +6
Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adopti…
Continual Learning of Context-dependent Processing in Neural Networks
Guanxiong Zeng, Yang Chen, Bo Cui +1
Deep neural networks (DNNs) are powerful tools in learning sophisticated but fixed mapping rules between inputs and outputs, thereby limiting their application in more complex and…
Structured Nonparametric Variational Inference for Dependent Latent Modeling
Yuda Shao, Zhiling Gu, Shan Yu
Variational inference (VI) is a core engine of modern AI, enabling scalable approximate Bayesian learning and uncertainty-aware training of large probabilistic and generative model…
Multi-Modal Latent Variables for Cross-Individual Primary Visual Cortex Modeling and Analysis
Yu Zhu, Bo Lei, Chunfeng Song +3
Elucidating the functional mechanisms of the primary visual cortex (V1) remains a fundamental challenge in systems neuroscience. Current computational models face two critical limi…
TQ-Net: Mixed Contrastive Representation Learning For Heterogeneous Test Questions
He Zhu, Xihua Li, Xuemin Zhao +2
Recently, more and more people study online for the convenience of access to massive learning materials (e.g. test questions/notes), thus accurately understanding learning material…
Per-RMAP: Feasibility-Seeking and Superiorization Methods for Floorplanning with I/O Assignment
Shan Yu, Yair Censor, Ming Jiang +1
The feasibility-seeking approach provides a systematic scheme to manage and solve complex constraints for continuous problems, and we explore it for the floorplanning problems with…
Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test
Guangfu Hao, Frederic Alexandre, Shan Yu
Cognitive flexibility has been extensively studied in human cognition but remains relatively unexplored in the context of Visual Large Language Models (VLLMs). This study assesses…
Multivariate Spline Estimation and Inference for Image-On-Scalar Regression
Shan Yu, Guannan Wang, Li Wang +1
Motivated by recent data analyses in biomedical imaging studies, we consider a class of image-on-scalar regression models for imaging responses and scalar predictors. We propose us…
Skeleton-Based Action Recognition with Synchronous Local and Non-local Spatio-temporal Learning and Frequency Attention
Guyue Hu, Bo Cui, Shan Yu
Benefiting from its succinctness and robustness, skeleton-based action recognition has recently attracted much attention. Most existing methods utilize local networks (e.g., recurr…
Visual Anomaly Detection for Reliable Robotic Implantation of Flexible Microelectrode Array
Yitong Chen, Xinyao Xu, Ping Zhu +3
Flexible microelectrode (FME) implantation into brain cortex is challenging due to the deformable fiber-like structure of FME probe and the interaction with critical bio-tissue. To…
AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViT
Fangbo Qin, Taogang Hou, Shan Lin +3
Towards flexible object-centric visual perception, we propose a one-shot instance-aware object keypoint (OKP) extraction approach, AnyOKP, which leverages the powerful representati…
Prognostication of chronic disorders of consciousness using brain functional networks and clinical characteristics
Ming Song, Yi Yang, Jianghong He +12
Disorders of consciousness are a heterogeneous mixture of different diseases or injuries. Although some indicators and models have been proposed for prognostication, any single met…
Nonparametric Density Estimation for Data Scattered on Irregular Spatial Domains: A Likelihood-Based Approach Using Bivariate Penalized Spline Smoothing
Kunal Das, Shan Yu, Guannan Wang +1
Accurately estimating data density is crucial for making informed decisions and modeling in various fields. This paper presents a novel nonparametric density estimation procedure t…
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Jin Gao, Yan Lu, Xiaojuan Qi +5
Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few…
VQPy: An Object-Oriented Approach to Modern Video Analytics
Shan Yu, Zhenting Zhu, Yu Chen +6
Video analytics is widely used in contemporary systems and services. At the forefront of video analytics are video queries that users develop to find objects of particular interest…
Individual brain parcellation: Review of methods, validations and applications
Chengyi Li, Shan Yu, Yue Cui
Individual brains vary greatly in morphology, connectivity and organization. The applicability of group-level parcellations is limited by the rapid development of precision medicin…
Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning
Guangfu Hao, Yuming Dai, Xianzhe Qin +1
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of language tasks, yet complex multi-step reasoning remains a fundamental challenge. Whil…
Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos
Polina Turishcheva, Paul G. Fahey, Michaela VystrÄilová +22
Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural…
Floorplanning with I/O assignment via feasibility-seeking and superiorization methods
Shan Yu, Yair Censor, Guojie Luo
The feasibility-seeking approach offers a systematic framework for managing and resolving intricate constraints in continuous problems, making it a promising avenue to explore in t…
Autoregressive Visual Decoding from EEG Signals
Sicheng Dai, Hongwang Xiao, Shan Yu +1
Electroencephalogram (EEG) signals have become a popular medium for decoding visual information due to their cost-effectiveness and high temporal resolution. However, current appro…
A ferroelectric-like structural transition in a metal
Youguo Shi, Yanfeng Guo, Xia Wang +13
Metals cannot exhibit ferroelectricity because static internal electric fields are screened by conduction electrons, but in 1965, Anderson and Blount predicted the possibility of a…
StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
Guoqing Ma, Xun Lin, Hui Ma +6
Most existing Face Forgery Detection (FFD) models assume access to raw face images. In practice, under a client-server framework, private facial data may be intercepted during tran…
Closed-Loop Knowledge Dynamics: An Operational Framework for Saturation and Escape
Xuening Wu, Shan Yu, Shenqin Yin
The paper proposes a framework for understanding why feedback loops in AI systems like large language models and reinforcement learning eventually stop improving, and how external…
Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder
Yuhan Zhang, Guoqing Ma, Guangfu Hao +3
While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of…
TSSS: A Novel Triangulated Spherical Spline Smoothing for Surface-based Data
Zhiling Gu, Shan Yu, Guannan Wang +2
Surface-based data is commonly observed in diverse practical applications spanning various fields. In this paper, we introduce a novel nonparametric method to discover the underlyi…
AI of Brain and Cognitive Sciences: From the Perspective of First Principles
Luyao Chen, Zhiqiang Chen, Longsheng Jiang +13
Nowadays, we have witnessed the great success of AI in various applications, including image classification, game playing, protein structure analysis, language translation, and con…
Nonparametric Regression for 3D Point Cloud Learning
Xinyi Li, Shan Yu, Yueying Wang +3
Over the past two decades, we have seen an exponentially increased amount of point clouds collected with irregular shapes in various areas. Motivated by the importance of solid mod…
AG-TAL: Anatomically-Guided Topology-Aware Loss for Multiclass Segmentation of the Circle of Willis Using Large-Scale Multi-Center Datasets
Jialu Liu, Yue Cui, Shan Yu
Accurate multiclass segmentation of the Circle of Willis (CoW) is essential for neurovascular disease management but remains challenging due to complex vascular topology and variab…
Superconductivity suppression of Ba0.5K0.5Fe2-2xM2xAs2 single crystals by substitution of transition-metal (M = Mn, Ru, Co, Ni, Cu, and Zn)
Jun Li, Yanfeng Guo, Shoubao Zhang +12
We investigated the doping effects of magnetic and nonmagnetic impurities on the single-crystalline p-type Ba0.5K0.5Fe2-2xM2xAs2 (M = Mn, Ru, Co, Ni, Cu and Zn) superconductors. Th…
GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning
Guoqing Ma, Siheng Wang, Zeyu Zhang +2
Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robo…
Ethosight: A Reasoning-Guided Iterative Learning System for Nuanced Perception based on Joint-Embedding & Contextual Label Affinity
Hugo Latapie, Shan Yu, Patrick Hammer +14
Traditional computer vision models often necessitate extensive data acquisition, annotation, and validation. These models frequently struggle in real-world applications, resulting…
Progressive Relation Learning for Group Activity Recognition
Guyue Hu, Bo Cui, Yuan He +1
Group activities usually involve spatiotemporal dynamics among many interactive individuals, while only a few participants at several key frames essentially define the activity. Th…
Linear decrease of critical temperature with increasing Zn substitution in the iron-based superconductor BaFe1.89-2xZn2xCo0.11As2
Jun Li, Yanfeng Guo, Shoubao Zhang +5
The nonmagnetic impurity effect is studied on the Fe-based BaFe1.89Co0.11As2 superconductor (Tc = 25 K) with Zn substitution for Fe up to 8 at. %, which is achieved by means of hig…
Effective Decision Boundary Learning for Class Incremental Learning
Kunchi Li, Jun Wan, Shan Yu
Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old class…
BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery
Xuening Wu, Shan Yu, Qianya Xu +1
Autonomous scientific discovery systems increasingly use large language models (LLMs) to propose new hypotheses, but many such systems condition primarily on experimental memory: a…
Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shift
Liangxuan Guo, Yang Chen, Shan Yu
Continual learning (CL) is an important technique to allow artificial neural networks to work in open environments. CL enables a system to learn new tasks without severe interferen…
Information capacity and transmission are maximized in balanced cortical networks with neuronal avalanches
Woodrow L. Shew, Hongdian Yang, Shan Yu +2
The repertoire of neural activity patterns that a cortical network can produce constrains the network's ability to transfer and process information. Here, we measured activity patt…
Energy-based Autoregressive Generation for Neural Population Dynamics
Ningling Ge, Sicheng Dai, Yu Zhu +1
Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computatio…
Robust Spatiotemporal Epidemic Modeling with Integrated Adaptive Outlier Detection
Haoming Shi, Shan Yu, Eric C. Chi
In epidemic modeling, outliers can distort parameter estimation and ultimately lead to misguided public health decisions. Although there are existing robust methods that can mitiga…
Universal Organization of Resting Brain Activity at the Thermodynamic Critical Point
Shan Yu, Hongdian Yang, Oren Shriki +1
Thermodynamic criticality describes emergent phenomena in a wide variety of complex systems. In the mammalian brain, the complex dynamics that spontaneously emerge from neuronal in…
BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed Cluster
Jason Dai, Ding Ding, Dongjie Shi +13
Most AI projects start with a Python notebook running on a single laptop; however, one usually needs to go through a mountain of pains to scale it to handle larger dataset (for bot…
Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation
Sicheng Dai, Kai Chen, Hongwang Xiao +2
Recent self-supervised pre-training methods for electroencephalogram (EEG) have shown promising results. However, the pre-trained models typically require full fine-tuning on each…
Intra-Class Uncertainty Loss Function for Classification
He Zhu, Shan Yu
Most classification models can be considered as the process of matching templates. However, when intra-class uncertainty/variability is not considered, especially for datasets cont…
Learning from Pattern Completion: Self-supervised Controllable Generation
Zhiqiang Chen, Guofan Fan, Jinying Gao +4
The human brain exhibits a strong ability to spontaneously associate different visual attributes of the same or similar visual scene, such as associating sketches and graffiti with…
DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency
Haoran Ma, Yifan Qiao, Shi Liu +7
Despite being a powerful concept, distributed shared memory (DSM) has not been made practical due to the extensive synchronization needed between servers to implement memory cohere…
Quantum mechanics needs no consciousness (and the other way around)
Shan Yu, Danko NikoliÄ
It has been suggested that consciousness plays an important role in quantum mechanics as it is necessary for the collapse of wave function during the measurement. Furthermore, this…
Adaptive Data Augmentation for Contrastive Learning
Yuhan Zhang, He Zhu, Shan Yu
In computer vision, contrastive learning is the most advanced unsupervised learning framework. Yet most previous methods simply apply fixed composition of data augmentations to imp…
Multi-dimensional Neural Decoding with Orthogonal Representations for Brain-Computer Interfaces
Kaixi Tian, Shengjia Zhao, Yuhan Zhang +1
Current brain-computer interfaces primarily decode single motor variables, limiting their ability to support natural, high-bandwidth neural control that requires simultaneous extra…
Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning
Shan Yu, Yifan Qiao, Mingyuan Ma +18
Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Ana…
Spatial Heterogeneous Additive Partial Linear Model: A Joint Approach of Bivariate Spline and Forest Lasso
Xin Zhang, Shan Yu, Zhengyuan Zhu +1
Identifying spatial heterogeneous patterns has attracted a surge of research interest in recent years, due to its important applications in various scientific and engineering field…
Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning
Guoqing Ma, Yuhan Zhang, Yuming Dai +3
Reinforcement learning (RL) has made significant advancements, achieving superhuman performance in various tasks. However, RL agents often operate under the assumption of environme…
Comparing and Integrating US COVID-19 Data from Multiple Sources with Anomaly Detection and Repairing
Guannan Wang, Zhiling Gu, Xinyi Li +5
Over the past few months, the outbreak of Coronavirus disease (COVID-19) has been expanding over the world. A reliable and accurate dataset of the cases is vital for scientists to…
Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving
Shan Yu, Junyi Shu, Yuanjiang Ni +14
As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing…
Spatiotemporal Dynamics, Nowcasting and Forecasting of COVID-19 in the United States
Li Wang, Guannan Wang, Lei Gao +5
Epidemic modeling is an essential tool to understand the spread of the novel coronavirus and ultimately assist in disease prevention, policymaking, and resource allocation. In this…
Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment
Yu Zhu, Chunfeng Song, Wanli Ouyang +2
Individual brains exhibit striking structural and physiological heterogeneity, yet neural circuits can generate remarkably consistent functional properties across individuals, an a…
A neural network for modeling human concept formation, understanding and communication
Liangxuan Guo, Haoyang Chen, Yang Chen +2
A remarkable capability of the human brain is to form more abstract conceptual representations from sensorimotor experiences and flexibly apply them independent of direct sensory i…
ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving
Yifan Qiao, Shu Anzai, Shan Yu +10
Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identi…
Nonparametric Automatic Differentiation Variational Inference with Spline Approximation
Yuda Shao, Shan Yu, Tianshu Feng
Automatic Differentiation Variational Inference (ADVI) is efficient in learning probabilistic models. Classic ADVI relies on the parametric approach to approximate the posterior. I…
UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing
Xinming Wei, Chao Jin, Tuo Dai +10
Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute straggle…
Emergence of Symbols in Neural Networks for Semantic Understanding and Communication
Yang Chen, Liangxuan Guo, Shan Yu
The capacity to generate meaningful symbols and effectively employ them for advanced cognitive processes, such as communication, reasoning, and planning, constitutes a fundamental…
Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
Zhenting Zhu, Lucas Thai, Shan Yu +5
As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict system requirement. While practi…