Publications (306)
Modeling Adaptive Tracking of Predictable Stimuli in Electric Fish
Yu Yang, Andreas Oliveira, Louis L. Whitcomb +3
The weakly electric fish \emph{Eigenmannia virescens} naturally swims back and forth to stay within a moving refuge, tracking its motion using visual and electrosensory feedback. P…
IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing
Tao Hu, Jiaxin Ai, Licheng Wen +12
Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismatch with iterative re…
Distributed Control of Multi-zone HVAC Systems Considering Indoor Air Quality
Yu Yang, Seshadhri Srinivasan, Guoqiang Hu +1
This paper studies a scalable control method for multi-zone heating, ventilation and air-conditioning (HVAC) systems to optimize the energy cost for maintaining thermal comfort and…
Finding Theme Communities from Database Networks
Lingyang Chu, Zhefeng Wang, Jian Pei +3
Given a database network where each vertex is associated with a transaction database, we are interested in finding theme communities. Here, a theme community is a cohesive subgraph…
End-to-End Learning-based Operation of Integrated Energy Systems for Buildings and Data Centers
Zhenyu Pu, Yu Yang, Liang Yu +1
Buildings and data centers (DCs) are energy-intensive sectors, playing a critical role to achieve the low-carbon and sustainable energy transition targets. To this end, integrated…
DQFormer: Towards Unified LiDAR Panoptic Segmentation with Decoupled Queries
Yu Yang, Jianbiao Mei, Liang Liu +6
LiDAR panoptic segmentation, which jointly performs instance and semantic segmentation for things and stuff classes, plays a fundamental role in LiDAR perception tasks. While most…
Robust Learning with Progressive Data Expansion Against Spurious Correlation
Yihe Deng, Yu Yang, Baharan Mirzasoleiman +1
While deep learning models have shown remarkable performance in various tasks, they are susceptible to learning non-generalizable spurious features rather than the core features th…
Learning A Universal Crime Predictor with Knowledge-guided Hypernetworks
Fidan Karimova, Tong Chen, Yu Yang +1
Predicting crimes in urban environments is crucial for public safety, yet existing prediction methods often struggle to align the knowledge across diverse cities that vary dramatic…
Personality Analysis from Online Short Video Platforms with Multi-domain Adaptation
Sixu An, Xiangguo Sun, Yicong Li +2
Personality analysis from online short videos has gained prominence due to its applications in personalized recommendation systems, sentiment analysis, and human-computer interacti…
Multiparameter simultaneous optimal estimation with an SU(2) coding unitary evolution
Yu Yang, Shihao Ru, Min An +4
In a ubiquitous dynamics, achieving the simultaneous optimal estimation of multiple parameters is significant but difficult. Using quantum control to optimize this …
Electronic, mechanical, and thermodynamic properties of americium dioxide
Yong Lu, Yu Yang, Fawei Zheng +2
By performing density functional theory (DFT) + calculations, we systematically study the electronic, mechanical, tensile, and thermodynamic properties of AmO. The experim…
DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes
Jianbiao Mei, Tao Hu, Xuemeng Yang +7
Recent advances in diffusion models have improved controllable streetscape generation and supported downstream perception and planning tasks. However, challenges remain in accurate…
Selling Renewable Utilization Service to Consumers via Cloud Energy Storage
Yu Yang, Utkarsha Agwan, Guoqiang Hu +1
This paper proposes a cloud energy storage (CES) model for enabling local renewable integration of building consumers (BCs). Different from most existing third-party based ES shari…
In-Network Neighborhood-Based Node Similarity Measure: A Unified Parametric Model
Yu Yang, Jian Pei
In many applications, we need to measure similarity between nodes in a large network based on features of their neighborhoods. Although in-network node similarity based on proximit…
Graph Neural Patching for Cold-Start Recommendations
Hao Chen, Yu Yang, Yuanchen Bei +3
The cold start problem in recommender systems remains a critical challenge. Current solutions often train hybrid models on auxiliary data for both cold and warm users/items, potent…
Pre-train and Fine-tune: Recommenders as Large Models
Zhenhao Jiang, Chenghao Chen, Hao Feng +5
In reality, users have different interests in different periods, regions, scenes, etc. Such changes in interest are so drastic that they are difficult to be captured by recommender…
The positive partial transpose conjecture for n=3
Lin Chen, Yu Yang, Waishing Tang
We present the PPT square conjecture introduced by M. Christandl. We prove the conjecture in the case as a consequence of the fact that two-qutrit PPT states have Schmidt at…
Eff-3DPSeg: 3D organ-level plant shoot segmentation using annotation-efficient point clouds
Liyi Luo, Xintong Jiang, Yu Yang +4
Reliable and automated 3D plant shoot segmentation is a core prerequisite for the extraction of plant phenotypic traits at the organ level. Combining deep learning and point clouds…
Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation
Hua Yan, Heng Tan, Yingxue Zhang +1
The paper introduces MobCache, a mobility-aware caching framework that stores and reuses latent-space embeddings of LLM reasoning steps to enable efficient large-scale human mobili…
An explicit basis for the rational higher Chow groups of abelian number fields
Matt Kerr, Yu Yang
We review and simplify A. Beilinson's construction of a basis for the motivic cohomology of a point over a cyclotomic field, then promote the basis elements to higher Chow cycles a…
Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation
Zhiyuan Wen, Jiannong Cao, Yu Yang +2
Personality Recognition in Conversation (PRC) aims to identify the personality traits of speakers through textual dialogue content. It is essential for providing personalized servi…
Large Language Model-Guided Semantic Alignment for Human Activity Recognition
Hua Yan, Heng Tan, Yi Ding +3
Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in…
The complexity of total edge domination and some related results on trees
Zhuo Pan, Yu Yang, Xianyue Li +1
For a graph with vertex set and edge set , a subset of is called an (resp. a ) if every e…
Quantum squeezing in a nonlinear mechanical oscillator
Stefano Marti, Uwe von Lüpke, Om Joshi +5
Mechanical degrees of freedom are natural candidates for continuous-variable quantum information processing and bosonic quantum simulations. These applications, however, require th…
Mechanism of the quasi-elastic scattering based on the dinuclear system concept
Zehong Liao, Yu Yang, Zepeng Gao +2
A unified description of full reaction channels in low-energy heavy-ion collisions is a great challenge. Although the theoretical models based on the dinuclear system (DNS) concept…
Constraining the Woods-Saxon potential in fusion reactions based on the neural network
Zepeng Gao, Siyu Liu, Peiwei Wen +5
The accurate determination of the nuclear interaction potential is essential for predicting the fusion cross sections and understanding the reaction mechanism, which plays an impor…
Randomized Algorithms For High Quality Treatment Planning in Volumetric Modulated Arc Therapy
Yu Yang, Bin Dong, Zaiwen Wen
In recent years, volumetric modulated arc therapy (VMAT) has been becoming a more and more important radiation technique widely used in clinical application for cancer treatment. O…
Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation
Weiwei Fang, Lin Li, Kaize Shi +2
High-fidelity social simulation is pivotal for addressing complex Web societal challenges, yet it demands agents capable of authentically replicating the dynamic spectrum of human…
Interpreting CNNs via Decision Trees
Quanshi Zhang, Yu Yang, Haotian Ma +1
This paper aims to quantitatively explain rationales of each prediction that is made by a pre-trained convolutional neural network (CNN). We propose to learn a decision tree, which…
Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures
Dang Nguyen, Wenhan Yang, Rathul Anand +2
Training with larger mini-batches improves the convergence rate and can yield superior performance. However, training with large mini-batches becomes prohibitive for Large Language…
Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
Chengyi Ju, Jiannong Cao, Yu Yang +2
In the era of modern education, addressing cross-school learner diversity is crucial, especially in personalized recommender systems for elective course selection. However, privacy…
Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency
Qixin Zhang, Zongqi Wan, Yu Yang +2
Coordinating multiple agents to collaboratively maximize submodular functions in unpredictable environments is a critical task with numerous applications in machine learning, robot…
LLaMA-Reg: Using LLaMA 2 for Unsupervised Medical Image Registration
Mingrui Ma, Yu Yang
Medical image registration is an essential topic in medical image analysis. In this paper, we propose a method for medical image registration using a pretrained large language mode…
Activated dissociation of O2 on Pb(111) surfaces by Pb adatoms
Yu Yang, Jia Li, Zhirong Liu +8
We investigate the dissociation of O2 on Pb(111) surface using first-principles calculations. It is found that in a practical high-vacuum environment, the adsorption of molecular O…
Two-parameter Hong-Ou-Mandel dip
Yu Yang, Luping Xu, Vittorio Giovannetti
A modification of the standard Hong-Ou-Mandel interferometer is proposed which allows one to replicate the celebrated coincidence dip in the case of two-independent delay parameter…
VeMo: Enabling Transparent Vehicular Mobility Modeling at Individual Levels with Full Penetration
Yu Yang, Xiaoyang Xie, Zhihan Fang +3
Understanding and predicting real-time vehicle mobility patterns on highways are essential to address traffic congestion and respond to the emergency. However, almost all existing…
A data-enabled physics-informed neural network with comprehensive numerical study on solving neutron diffusion eigenvalue problems
Yu Yang, Helin Gong, Shiquan Zhang +4
We present a data-enabled physics-informed neural network (DEPINN) with comprehensive numerical study for solving industrial scale neutron diffusion eigenvalue problems (NDEPs). In…
ReLeTA: Reinforcement Learning for Thermal-Aware Task Allocation on Multicore
Shi-Gui Yang, Yuan-Yuan Wang, Di Liu +4
In this paper, we propose \textit{ReLeTA}: Reinforcement Learning based Task Allocation for temperature minimization. We design a new reward function and use a new state model to f…
Feasibility of Local Trajectory Planning for Level-2+ Semi-autonomous Driving without Absolute Localization
Sheng Zhu, Jiawei Wang, Yu Yang +1
Autonomous driving has long grappled with the need for precise absolute localization, making full autonomy elusive and raising the capital entry barriers for startups. This study d…
Spontaneous Repairing Liquid Metal/Si Nanocomposite as a Smart Conductive-Additive-Free Anode for Lithium-ion Battery
Bing Han, Yu Yang, Xiaobo Shi +7
Silicon is a promising candidate for negative electrodes due to its high theoretical specific capacity (~3579 mAh g-1) and low lithiation potential (~0.40 V vs Li). However, its pr…
Tracking Top-K Influential Vertices in Dynamic Networks
Yu Yang, Zhefeng Wang, Tianyuan Jin +2
Influence propagation in networks has enjoyed fruitful applications and has been extensively studied in literature. However, only very limited preliminary studies tackled the chall…
On the uncertainty analysis of the data-enabled physics-informed neural network for solving neutron diffusion eigenvalue problem
Yu Yang, Helin Gong, Qihong Yang +3
In practical engineering experiments, the data obtained through detectors are inevitably noisy. For the already proposed data-enabled physics-informed neural network (DEPINN) \cite…
Influence of database noises to machine learning for spatiotemporal chaos
Yu Yang, Shijie Qin, Shijun Liao
A new strategy, namely the "clean numerical simulation" (CNS), was proposed (J. Computational Physics, 418:109629, 2020) to gain reliable/convergent simulations (with negligible nu…
PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation
Jianbiao Mei, Yu Yang, Mengmeng Wang +3
Reliable LiDAR panoptic segmentation (LPS), including both semantic and instance segmentation, is vital for many robotic applications, such as autonomous driving. This work propose…
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
Yi Zeng, Kevin Klyman, Andy Zhou +6
We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a sig…
An Equivalent and Unified Virtual Battery Modeling Framework for Flexibility Characterization of Building HVAC Systems
Qi Zhu, Yu Yang, Liang Yu +3
The heating, ventilation and air-conditioning (HVAC) system dominates building's energy consumption and meanwhile exhibits substantial operational flexibility that can be exploited…
Activity Maximization by Effective Information Diffusion in Social Networks
Zhefeng Wang, Yu Yang, Jian Pei +1
In a social network, even about the same information the excitements between different pairs of users are different. If you want to spread a piece of new information and maximize t…
Maximums of generalized Hasse-Witt invariants and their applications to anabelian geometry
Yu Yang
Let be an arbitrary pointed stable curve of topological type over an algebraically closed field of characteristic . We prove that the generalized…
Not All Poisons are Created Equal: Robust Training against Data Poisoning
Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman
Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only again…
A Multi-Level Deep Framework for Deep Solvers of Partial Differential Equations
Yu Yang, Qiaolin He
In this paper, inspired by the multigrid method, we propose a multi-level deep framework for deep solvers. Overall, it divides the entire training process into different levels of…
AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies
Yi Zeng, Yu Yang, Andy Zhou +9
Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and…
FDIO: Frequency Decomposed Inertial Odometry
Shanshan Zhang, Liqin Wu, Wenying Cao +2
Pedestrian inertial odometry (PIO) estimates autonomous pedestrian motion using only acceleration and angular velocity measurements collected by an inertial measurement unit (IMU),…
Analysing symbolic data by pseudo-marginal methods
Yu Yang, Matias Quiroz, Boris Beranger +2
Symbolic data analysis (SDA) aggregates large individual-level datasets into a small number of distributional summaries, such as random rectangles or random histograms. The inferen…
Slender Origami with Complex 3D Folding Shapes
Soroush Kamrava, Ranajay Ghosh, Yu Yang +1
One-dimensional slender bodies can be deformed or shaped into spatially complex curves relatively easily due to their inherent compliance. However, traditional methods of fabricati…
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
Yihao Xue, Ali Payani, Yu Yang +1
Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments. When obtaining labeled data from the target distribution is e…
Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning
Zhangjie Xia, Yu Yang, Pan Xu
Off-dynamics offline reinforcement learning (RL) aims to learn a policy for a target domain using limited target data and abundant source data collected under different transition…
A correlated pseudo-marginal approach to doubly intractable problems
Yu Yang, Matias Quiroz, Robert Kohn +1
Doubly intractable models are encountered in a number of fields, e.g. social networks, ecology and epidemiology. Inference for such models requires the evaluation of a likelihood f…
eBrainII: A 3 kW Realtime Custom 3D DRAM integrated ASIC implementation of a Biologically Plausible Model of a Human Scale Cortex
Dimitrios Stathis, Chirag Sudarshan, Yu Yang +6
The Artificial Neural Networks (ANNs) like CNN/DNN and LSTM are not biologically plausible and in spite of their initial success, they cannot attain the cognitive capabilities enab…
Quantum size effect on the dissociation of O2 molecules on ultrathin Pb(111) films
Ziyu Hu, Yu Yang, Bo Sun +5
Using first-principles calculations, we systematically study the dissociation of O molecules on different ultrathin Pb(111) films. Based on our previous work revealing the mole…
Untwining multiple parameters at the exclusive zero-coincidence points with quantum control
Yu Yang, Federico Belliardo, Vittorio Giovannetti +1
In this paper we address a special case of "sloppy" quantum estimation procedures which happens in the presence of intertwined parameters. A collection of parameters are said to be…
Shell effects on the drift and fluctuation in multinucleon transfer reactions
Zehong Liao, Zepeng Gao, Yu Yang +2
This study employs the dinuclear system model (DNS-sysu) to investigate drift and fluctuation mechanisms in 136Xe + 209Bi collisions above the Coulomb barrier. The DNS-sysu model d…
Electron correlation and spin-orbit coupling effects in US3 and USe3
Yu Yang, Wei Yang, Ping Zhang
A systematic density functional theory (DFT)+U study is conducted to investigate the electron correlation and spin-orbit coupling (SOC) effects in US3 and USe3. Our calculations re…
ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
Dunwei Tu, Hongyan Hao, Hansi Yang +10
Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scar…
Moving Sampling Physics-informed Neural Networks induced by Moving Mesh PDE
Yu Yang, Qihong Yang, Yangtao Deng +1
In this work, we propose an end-to-end adaptive sampling neural network (MMPDE-Net) based on the moving mesh method, which can adaptively generate new sampling points by solving th…
Revealing spatio-temporal interaction patterns behind complex cities
Chenxin Liu, Yu Yang, Bingsheng Chen +4
Cities are typical dynamic complex systems that connect people and facilitate interactions. Revealing universal collective patterns behind spatio-temporal interactions between resi…
Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization
Qixin Zhang, Zengde Deng, Xiangru Jian +3
Maximizing a monotone submodular function is a fundamental task in machine learning, economics, and statistics. In this paper, we present two communication-efficient decentralized…
On the Stability of Expressive Positional Encodings for Graphs
Yinan Huang, William Lu, Joshua Robinson +4
Designing effective positional encodings for graphs is key to building powerful graph transformers and enhancing message-passing graph neural networks. Although widespread, using L…
Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models
Zhiyuan Wen, Yu Yang, Jiannong Cao +3
As large language models (LLMs) appear to behave increasingly human-like in text-based interactions, more and more researchers become interested in investigating personality in LLM…
Predicting Student Dropout Risk With A Dual-Modal Abrupt Behavioral Changes Approach
Jiabei Cheng, Zhen-Qun Yang, Jiannong Cao +2
Timely prediction of students at high risk of dropout is critical for early intervention and improving educational outcomes. However, in offline educational settings, poor data qua…
Camera-based 3D Semantic Scene Completion with Sparse Guidance Network
Jianbiao Mei, Yu Yang, Mengmeng Wang +5
Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for au…
Building the Chessboard-like Supramolecular Structure on Au (111) Surfaces
Ruifen Dou, Yu Yang, Ping Zhang +4
We investigate an anthracene derivative, 3(5)-(9-anthryl) pyrazole (ANP), self-assembled on the Au (111) surface by means of scanning tunneling microscopy (STM) and density functio…
Towards Event-Robust Acoustic Scene Classification
Yiqiang Cai, Bohan Hu, Yu Yang +3
The paper presents the Event-Shifted Acoustic Scene (ESAS) dataset, a benchmark that adds foreground sound events to background scenes to test how well acoustic scene classificatio…
A mechanical qubit
Yu Yang, Igor Kladaric, Maxwell Drimmer +6
Strong nonlinear interactions between quantized excitations are an important resource for quantum technologies based on bosonic oscillator modes. However, most electromagnetic and…
Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models
Rong Zhou, Dongping Chen, Zihan Jia +24
Digital twins, as precise digital representations of physical systems, have evolved from passive simulation tools into intelligent and autonomous entities through the integration o…
Rate-Distortion-Perception Tradeoff for the Gray-Wyner Problem
Yu Yang, Yingxin Zhang, Weijie Yuan +1
We revisit the Gray-Wyner lossy source coding problem and derive the first-order asymptotic optimal rate-distortion-perception region when additional perception constraints are imp…
Purifying one-neutron removal as a probe of single-particle strength
Erxi Xiao, Guangshuai Li, Yu Yang +4
One-neutron removal reactions exhibit a strong proton-neutron asymmetry dependence in the inclusive reduction factor , a long-standing issue that has been discussed in terms o…
New insight into the N/Z and mass equilibration in heavy-ion collisions
Yu Yang, Zehong Liao, Zepeng Gao +3
The dynamics of N/Z and mass equilibration are investigated in the reactions 112,124Sn + 239Pu by employing the isospin-dependent quantum molecular dynamics model. It is found that…
Raman Spectroscopy Insights into the Reorientational Dynamics of Polyanions in Solid Electrolytes
Jianghai Chen, Yu Yang, Ya Tang +2
The interaction between cation diffusion and polyanion rotational dynamics has garnered significant attention, yet characterizing the rotational dynamics of polyanions remains chal…
Local Manifold Augmentation for Multiview Semantic Consistency
Yu Yang, Wing Yin Cheung, Chang Liu +1
Multiview self-supervised representation learning roots in exploring semantic consistency across data of complex intra-class variation. Such variation is not directly accessible an…
MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning
Yihong Guo, Yu Yang, Pan Xu +1
We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods…
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function
Qixin Zhang, Zengde Deng, Zaiyi Chen +2
In this paper, we revisit Stochastic Continuous Submodular Maximization in both offline and online settings, which can benefit wide applications in machine learning and operations…
X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability
Yu Yang, Alan Liang, Jianbiao Mei +3
Diffusion models are advancing autonomous driving by enabling realistic data synthesis, predictive end-to-end planning, and closed-loop simulation, with a primary focus on temporal…
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Haque Ishfaq, Yixin Tan, Yu Yang +5
Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to im…
Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations
Zilin Wang, Haolin Zhuang, Lu Li +6
This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation…
Observation of Moiré Time Crystal in Floquet-driven Rydberg Atomic Gases
Shuai Shi, Dong-Yang Zhu, Yu Yang +8
The authors experimentally realize a Moiré time crystal in a Floquet-driven Rydberg atomic gas by using a bichromatic driving field, revealing a comb-like beat pattern and mapping…
Comprehensive Performance Evaluation of LID Practices for the Sponge City Construction: A Case Study in Guangxi, China
Li Qian, Wang Feng, Yu Yang +3
Sponge city construction is a new concept of urban stormwater management, which can effectively relieve urban flooding, reduce non-point source pollution, and promote the usage of…
CIS: Composable Instruction Set for Data Streaming Applications
Yu Yang, Jordi Altayó González, Paul Delestrac +1
The enhanced efficiency of hardware accelerators, including Single Instruction Multiple Data (SIMD) architectures and Coarse-Grained Reconfigurable Architectures (CGRAs), is drivin…
Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients
Jiafei Lyu, Yu Yang, Jiangpeng Yan +1
It is vital to accurately estimate the value function in Deep Reinforcement Learning (DRL) such that the agent could execute proper actions instead of suboptimal ones. However, exi…
A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
Lior Deutsch, Erik Nijkamp, Yu Yang
Recent work on mode connectivity in the loss landscape of deep neural networks has demonstrated that the locus of (sub-)optimal weight vectors lies on continuous paths. In this wor…
CKANIO: Learnable Chebyshev Polynomials for Inertial Odometry
Shanshan Zhang, Siyue Wang, Tianshui Wen +7
Inertial odometry (IO) relies exclusively on signals from an inertial measurement unit (IMU) for localization and offers a promising avenue for consumer grade positioning. However,…
Neural Networks Based on Power Method and Inverse Power Method for Solving Linear Eigenvalue Problems
Qihong Yang, Yangtao Deng, Yu Yang +2
In this article, we propose two kinds of neural networks inspired by power method and inverse power method to solve linear eigenvalue problems. These neural networks share similar…
A Proximal Linearization-based Decentralized Method for Nonconvex Problems with Nonlinear Constraints
Yu Yang, Guoqiang Hu, Costas J. Spanos
Decentralized optimization for non-convex problems are now demanding by many emerging applications (e.g., smart grids, smart building, etc.). Though dramatic progress has been achi…
Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)
Quanshi Zhang, Yu Yang, Ying Nian Wu
This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses i…
Floquet quantum multiparameter estimation with periodic-driving-induced topological phase transition
Yu Yang, Yuyang Tang, Pei Zhang +1
Periodically driven systems provide a powerful platform for quantum multiparameter estimation. Constructing a static effective Hamiltonian in a proper rotating frame is commonly em…
Towards Transactive Energy: An Analysis of Information-related Practical Issues
Yue Chen, Yu Yang, Xiaoyuan Xu
The development of distributed energy resources, such as rooftop photovoltaic (PV) panels, batteries, and electric vehicles (EVs), has decentralized our power system operation, whe…
Role of the isospin diffusion on cluster transfer in C + Bi reactions
Zepeng Gao, Yinu Zhang, Long Zhu +4
Heavy-ion collisions at near-barrier energies provide a crucial pathway for investigating nucleon correlations and clustering structures. Recent experimental results showed that th…
Battery Valuation and Management for Battery Swapping Station with an Intertemporal Framework
Xinjiang Chen, Yu Yang, Jianxiao Wang +2
Battery swapping as a business model for battery energy storage (BES) has great potential in future integrated low-carbon energy and transportation systems. However, frequent batte…
FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs
Haoran Lin, Xianzhi Yu, Kang Zhao +17
FlashAttention series has been widely applied in the inference of large language models (LLMs). However, FlashAttention series only supports the high-level GPU architectures, e.g.,…
O-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
Jianbiao Mei, Tao Hu, Daocheng Fu +11
Large Language Models (LLMs), despite their advancements, are fundamentally limited by their static parametric knowledge, hindering performance on tasks requiring open-domain up-to…
A novel number-theoretic sampling method for neural network solutions of partial differential equations
Yu Yang, Pingan He, Xiaoling Peng +1
Traditional Monte Carlo integration using uniform random sampling exhibits degraded efficiency in low-regularity or high-dimensional problems. We propose a novel deep learning fram…