Publications (1.5k)
Benchmark for Non-reciprocal Attack Detection on Synchronization
Zishuo Ren, Yiting Lin, Yufei Zhang +3
A precise and secure time synchronization is the backbone of both fundamental physics and advanced technologies. Despite ultra-high precision, security, particularly the unresolved…
Efficient Training of the Memristive Deep Belief Net Immune to Non-Idealities of the Synaptic Devices
Wei Wang, Barak Hoffer, Tzofnat Greenberg-Toledo +8
The tunability of conductance states of various emerging non-volatile memristive devices emulates the plasticity of biological synapses, making it promising in the hardware realiza…
Identification of cancer omics commonality and difference via community fusion
Yifan Sun, Yu Jiang, Yang Li +1
The analysis of cancer omics data is a "classic" problem, however, still remains challenging. Advancing from early studies that are mostly focused on a single type of cancer, some…
DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
Debin Meng, Jiaming Yang, Zefang Zong +4
The paper introduces DataClawEval, a benchmark that tests autonomous LLM agents on end-to-end data engineering tasks across multiple production-grade SQL and Spark engines using de…
EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents
Yu Zhang, Kaiyuan Shen, Yang Li
We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time…
The Bell-Bloom-type optically-pumped FID Rubidium atomic magnetometer with a multi-passing probe beam and two counter-propagating pump beams
Yongbiao Yang, Zhengyu Su, Yang Li +4
The Bell-Bloom-type optically pumped atomic magnetometers are well suited for weak geomagnetic field detection. However, conventional single-beam pumping introduces an atomic spin…
Meta CLIP 2: A Worldwide Scaling Recipe
Yung-Sung Chuang, Yang Li, Dong Wang +13
Contrastive Language-Image Pretraining (CLIP) is a popular foundation model, supporting from zero-shot classification, retrieval to encoders for multimodal large language models (M…
Attribute-aware Pedestrian Detection in a Crowd
Jialiang Zhang, Lixiang Lin, Yang Li +4
Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep…
Longitudinal dynamics for mesons on the light cone
Yang Li, James P. Vary
We survey a set of proposed light-front models for confinement in the valence quark sector of the mesons and portray similarities as well as differences. We present the spectroscop…
Group field theory for quantum gravity minimally coupled to a scalar field
Yang Li, Daniele Oriti, Mingyi Zhang
We construct a group field theory model for quantum gravity minimally coupled to relativistic scalar fields, defining as well a corresponding discrete gravity path integral (and, i…
Quarkonium wave functions on the light front
Yang Li
We study heavy quarkonium within the light-front Hamiltonian formalism. Our effective Hamiltonian is based on the holographic QCD confining potential and the one-gluon exchange int…
Generalized Extended Codes with Applications in Entanglement-Assisted Qubit and Qutrit Codes
Yang Li, Martianus Frederic Ezerman, Shitao Li +2
We prove that any generalized extended code is monomially equivalent to the Hermitian dual of a code which is closely related to a second kind of extended code of $\C^{\perp_{\rm H…
Similarity-based context aware continual learning for spiking neural networks
Bing Han, Feifei Zhao, Yang Li +3
Biological brains have the capability to adaptively coordinate relevant neuronal populations based on the task context to learn continuously changing tasks in real-world environmen…
What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning
Yang Li, Thomas Strohmer
Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in parti…
OpenBox: A Python Toolkit for Generalized Black-box Optimization
Huaijun Jiang, Yu Shen, Yang Li +5
Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, experimental design, and database knob tuning. However, users still face chall…
STEP3-VL-10B Technical Report
Ailin Huang, Chengyuan Yao, Chunrui Han +90
We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-…
Private Transformer Inference in MLaaS: A Survey
Yang Li, Xinyu Zhou, Yitong Wang +2
Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service (MLaaS)…
Matrix: Peer-to-Peer Multi-Agent Synthetic Data Generation Framework
Dong Wang, Yang Li, Ansong Ni +12
Synthetic data has become increasingly important for training large language models, especially when real data is scarce, expensive, or privacy-sensitive. Many such generation task…
Flemme: A Flexible and Modular Learning Platform for Medical Images
Guoqing Zhang, Jingyun Yang, Yang Li
As the rapid development of computer vision and the emergence of powerful network backbones and architectures, the application of deep learning in medical imaging has become increa…
Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019
Zhang Li, Jiehua Zhang, Tao Tan +30
Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in…
Universal characteristics of one-dimensional non-Hermitian superconductors
Yang Cao, Yang Li, Yuanping Chen +1
We establish a non-Bloch band theory for one-dimensional(1D) non-Hermitian topological superconductors. The universal physical properties of non-Hermitian topological superconducto…
Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization
Bingqing Zhang, Zhuo Cao, Heming Du +4
Despite recent advances, Text-to-video retrieval (TVR) is still hindered by multiple inherent uncertainties, such as ambiguous textual queries, indistinct text-video mappings, and…
Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models
Forrest Huang, Gang Li, Xin Zhou +2
The design process of user interfaces (UIs) often begins with articulating high-level design goals. Translating these high-level design goals into concrete design mock-ups, however…
A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
Bin Fu, Yunqi Qiu, Chengguang Tang +3
Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowled…
PRNet: Original Information Is All You Have
PeiHuang Zheng, Yunlong Zhao, Zheng Cui +1
Small object detection in aerial images suffers from severe information degradation during feature extraction due to limited pixel representations, where shallow spatial details fa…
Automatic Macro Mining from Interaction Traces at Scale
Forrest Huang, Gang Li, Tao Li +1
Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile inte…
Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling
Guobin Shen, Dongcheng Zhao, Yiting Dong +4
Within the complex neuroarchitecture of the brain, astrocytes play crucial roles in development, structure, and metabolism. These cells regulate neural activity through tripartite…
Cross-Utterance Conditioned VAE for Speech Generation
Yang Li, Cheng Yu, Guangzhi Sun +8
Speech synthesis systems powered by neural networks hold promise for multimedia production, but frequently face issues with producing expressive speech and seamless editing. In res…
Adaptive Progressive Attention Graph Neural Network for EEG Emotion Recognition
Tianzhi Feng, Chennan Wu, Yi Niu +5
In recent years, numerous neuroscientific studies demonstrate that specific areas of the brain are connected to human emotional responses, with these regions exhibiting variability…
Wings: Learning Multimodal LLMs without Text-only Forgetting
Yi-Kai Zhang, Shiyin Lu, Yang Li +7
Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophical…
Controlled islanding for a hybrid AC/DC grid with VSC-HVDC using semi-supervised spectral clustering
Yang Li, Shangsong Wu
As the last resort of emergency control, controlled islanding is an effective means of preventing fault-propagation and a system-wide blackout. However, conventional AC transmissio…
BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model
Yang Li, Chunhe Xia, Chang Li +1
With the increasing importance of machine learning, the privacy and security of training data have become critical. Federated learning, which stores data in distributed nodes and s…
Smart Tracking Tray System for A Smart and Sustainable Wet Lab Community
Nan Xu, Jingchen Li, Yue Yu +2
The laboratories and research institutes are the major places for cutting-edge scientific exploration. Hundreds of millions of research papers were formed from front-line labs. Beh…
A novel method of restoration path optimization for the AC-DC bulk power grid after a major blackout
Chao Yang, Gaoshen Liang, Tianle Cheng +2
The restoration control of the modern alternating current-direct current (AC-DC) hybrid power grid after a major blackout is difficult and complex. Taking into account the interact…
Properties and Decoding of Twisted GRS Codes and Their Extensions
Yang Li, Martianus Frederic Ezerman, Huimin Lao +1
Maximum distance separable (MDS) codes that are not equivalent to generalized Reed-Solomon (GRS) codes are called non-GRS MDS codes. Alongside near MDS (NMDS) codes, they are appli…
Topological energy braiding of the non-Bloch bands
Yang Li, Xiang Ji, Yuanping Chen +2
The non-Hermitian skin effect, as a unique feature of non-Hermitian systems, will break the topological energy braiding of the Bloch bands in open boundary systems. Going beyond th…
Bubbling phenomenon for Hermitian Yang-Mills connections
Yang Li
We construct local examples of singular Hermitian Yang-Mills connections over with uniformly bounded -energy, but the number of essential singular po…
Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence
Xiang He, Dongcheng Zhao, Yang Li +3
Multimodal learning enhances the perceptual capabilities of cognitive systems by integrating information from different sensory modalities. However, existing multimodal fusion rese…
Parton Distribution Functions of Heavy Mesons on the Light Front
Jiangshan Lan, Chandan Mondal, Meijian Li +4
The parton distribution functions (PDFs) of heavy mesons are evaluated from their light-front wave functions, which are obtained from a basis light-front quantization in the leadin…
Probabilistic Classification Vector Machine for Multi-Class Classification
Shengfei Lyu, Xing Tian, Yang Li +2
The probabilistic classification vector machine (PCVM) synthesizes the advantages of both the support vector machine and the relevant vector machine, delivering a sparse Bayesian s…
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
Xiang Huang, Zhanhong Ye, Hongsheng Liu +11
Many important problems in science and engineering require solving the so-called parametric partial differential equations (PDEs), i.e., PDEs with different physical parameters, bo…
Ovis: Structural Embedding Alignment for Multimodal Large Language Model
Shiyin Lu, Yang Li, Qing-Guo Chen +4
Current Multimodal Large Language Models (MLLMs) typically integrate a pre-trained LLM with another pre-trained vision transformer through a connector, such as an MLP, endowing the…
Some New Ramanujan's Modular Equations of Degree 15
Zhang Chuan-Ding, Yang Li
Ramanujan in his notebook recorded two modular equations involving multiplier with moduli of degrees (1,7) and (1,23). In this paper, we find some new Ramanujan's modular equations…
EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet
Yitao Yuan, Jianglong Nie, Tianyu Bai +28
In-Network Collective (INC) acceleration holds immense potential for optimizing AI training and inference; however, its cross-layer nature has historically hindered investment and…
Multi-level context Modeling for consistent expert selection in Mixture-of-Experts
Shuhan Huang, Naifan Zhang, Yuanbo Tang +2
Mixture-of-Experts (MoE) enables efficient scaling of Transformer models by routing tokens to a small subset of experts. However, existing routers typically condition expert select…
Hyperon-Nucleon Spectrometer
Xiaozhi Bai, Xu Cao, Zhe Cao +237
Chirality lies at the heart of low-energy QCD, governing the symmetry structure that shapes hadron masses and strong interaction dynamics. Among the most compelling open questions…
Optical anapole mode in nanostructured lithium niobate for enhancing second harmonic generation
Yang Li, Zhijin Huang, Zhan Sui +9
Second harmonic generation (SHG) with a material of large transparency is an attractive way of generating coherent light sources at exotic wavelength range such as VUV, UV and visi…
Predicting Human Performance in Vertical Menu Selection Using Deep Learning
Yang Li, Samy Bengio, Gilles Bailly
Predicting human performance in interaction tasks allows designers or developers to understand the expected performance of a target interface without actually testing it with real…
VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation
Qianxi Hua, Xinyue Li, Zheng Yan +4
Embodied intelligence has advanced rapidly in recent years; however, bimanual manipulation-especially in contact-rich tasks remains challenging. This is largely due to the lack of…
Monolithic CMOS-compatible zero-index metamaterials
Daryl I. Vulis, Yang Li, Orad Reshef +5
Zero-index materials exhibit exotic optical properties that can be utilized for integrated-optics applications. However, practical implementation requires compatibility with comple…
Open-World Reinforcement Learning over Long Short-Term Imagination
Jiajian Li, Qi Wang, Yunbo Wang +4
Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by…
Subjective-Objective Median-based Importance Technique (SOMIT) to Aid Multi-Criteria Renewable Energy Evaluation
Ding Ding, Yang Li, Poh Ling Neo +2
Accelerating the renewable energy transition requires informed decision-making that accounts for the diverse financial, technical, environmental, and social trade-offs across diffe…
Practical Continuous-variable Quantum Key Distribution with Feasible Optimization Parameters
Li Ma, Jie Yang, Tao Zhang +12
Continuous-variable quantum key distribution (CV-QKD) offers an approach to achieve a potential high secret key rate (SKR) in metropolitan areas. There are several challenges in de…
Generating Automatic Feedback on UI Mockups with Large Language Models
Peitong Duan, Jeremy Warner, Yang Li +1
Feedback on user interface (UI) mockups is crucial in design. However, human feedback is not always readily available. We explore the potential of using large language models for a…
NMR and Mossbauer study of spin dynamics and electronic structure of Fe{2+x}V{1-x}Al and Fe2VGa
C. S. Lue, Yang Li, Joseph H. Ross +1
In order to assess the magnetic ordering process in Fe2VAl and the related material Fe2VGa, we have carried out nuclear magnetic resonance (NMR) and Mossbauer studies. 27Al NMR rel…
Dimensional Crossover and Topological Phase Transition in Dirac Semimetal Na3Bi Films
Huinan Xia, Yang Li, Min Cai +7
Three-dimensional (3D) topological Dirac semimetal, when thinned down to 2D few layers, is expected to possess gapped Dirac nodes via quantum confinement effect and concomitantly d…
Spectrum of diffractively produced gluons in onium-nucleus collisions
Yang Li, Kirill Tuchin
We calculate spectrum of diffractively produced gluons in onium-heavy nucleus collisions at high energies. We show that it exhibits a characteristic dependence on nucleus atomic nu…
Coupled atomic motion and spin-glass transition in FeAl2
Yang Li, F. G. Vagizov, V. Goruganti +5
We have used 57Fe Mossbauer spectroscopy and x-ray diffraction to study the magnetic and vibrational properties of FeAl2. FeAl2 is an ordered intermetallic with a large Fe local mo…
CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning
Junru Song, Wenhao Zhang, Yang Yang +7
Target-oriented vision-and-language navigation (VLN) on aerial platforms is attracting growing attention for missions such as disaster rescue, infrastructure inspection, and securi…
Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models
Dayu Wang, Jiaye Yang, Weikang Li +4
Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in interme…
StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems
Sergey Volkov, Yang Li, Ye Luo
Agent systems accumulate conflicting observations across branches, retries, and replicas, yet many practical memory layers still collapse disagreement behind overwrite rules that a…
The polarization and the fundamental sensitivity of K (Cs)-Rb-He hybrid optical pumping spin exchange relaxation free atomic magnetometers
Jian-Hua Liu, Dong-Yang Jing, Liang-Liang Wang +4
The hybrid optical pumping spin exchange relaxation free (SERF) atomic magnetometers can realize ultrahigh sensitivity measurement of magnetic field and inertia. We have studied th…
A CT Geometry With Multiple Centers Of Rotation For Solving Sparse View Problem
Jiayu Duan, Yang Li, Jianmei Cai +1
With the emergence of CNT (Carbon nanotube), static and instant CT scanning becomes possible. By transforming the traditionally rotated thermal source into a static ring array sour…
GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals
Yimin Hou, Shuyue Jia, Xiangmin Lun +5
Towards developing effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by electroencephalogram (EEG), is highly demanded. Tr…
Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness
Yang Li, Hai Liu, Dian Shao +8
Optimizing agentic workflows, such as retrieval-augmented generation (RAG) pipelines, requires navigating a combinatorial space of discrete component choices under tight evaluation…
User-generated Video Quality Assessment: A Subjective and Objective Study
Yang Li, Shengbin Meng, Xinfeng Zhang +3
Recently, we have observed an exponential increase of user-generated content (UGC) videos. The distinguished characteristic of UGC videos originates from the video production and d…
Indicator & crowding Distance-Based Evolutionary Algorithm for Combined Heat and Power Economic Emission Dispatch
Jiaze Sun, Jiahui Deng, Yang Li
Heat and power have become the most indispensable resources. However, the traditional ways of generating power and heat are inefficient and cause high pollution; a CHP (Combined He…
IMPACT: Importance-Aware Activation Space Reconstruction
Md Mokarram Chowdhury, Daniel Agyei Asante, Ernie Chang +1
Large language models (LLMs) achieve strong performance across diverse domains but remain difficult to deploy in resource-constrained environments due to their size. Low-rank compr…
AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control
Xiangyi Wei, Fei Wang, Haotian Zhang +6
Chemical laboratory automation has long been constrained by rigid workflows and poor adaptability to the long-tail distribution of experimental tasks. While most automated platform…
On Galois self-orthogonal algebraic geometry codes
Yun Ding, Shixin Zhu, Xiaoshan Kai +1
Galois self-orthogonal (SO) codes are generalizations of Euclidean and Hermitian SO codes. Algebraic geometry (AG) codes are the first known class of linear codes exceeding the Gil…
Proxy Reconstruction Pre-training for Ramp Flow Prediction at Highway Interchanges
Yongchao Li, Jun Chen, Zhuoxuan Li +4
Interchanges are crucial nodes for vehicle transfers between highways, yet the lack of real-time ramp detectors creates blind spots in traffic prediction. To address this, we propo…
Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning
Bryan Wang, Gang Li, Xin Zhou +3
Mobile User Interface Summarization generates succinct language descriptions of mobile screens for conveying important contents and functionalities of the screen, which can be usef…
Energy dissipation and angular momentum transfer within a magnetically torqued accretion disc
Zhao-Ming Gan, Ding-Xiong Wang, Wei-Hua Lei +1
We discuss transportation and redistribution of energy and angular momentum in the magnetic connection (MC) process and Blandford-Payne (BP) process. The MC results in readjusting…
From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks
Changpeng Yang, Jinyang Wu, Yuchen Liu +9
Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each…
Collaborative Learning for Extremely Low Bit Asymmetric Hashing
Yadan Luo, Zi Huang, Yang Li +3
Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression. Nevertheless, existing approaches could hardly g…
MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Model
Yifan Wu, Min Zeng, Yang Li +2
Most current molecular language models transfer the masked language model or image-text generation model from natural language processing to molecular field. However, molecules are…
The effect of dipole-dipole interaction for two atoms with different couplings in non-Markovian environment
Yang Li, Jiang Zhou, Hong Guo
Using the nonperturbative method, we study the exact entanglement dynamics of two two-level dipole-dipole interacting atoms coupled to a common non-Markovian reservoir with differe…
ATGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of i…
Shape, regolith size and thickness, SMFe^0 content, and spectral type of Tianwen-2 target asteroid (469219) Kamo'oalewa
Pengfei Zhang, Guozheng Zhang, Yongxiong Zhang +13
China's Tianwen-2 spacecraft will return samples from the near-Earth asteroid (469219) Kamo'oalewa. We previously reported that Kamo'oalewa develops an LL-chondrite-compositional,…
Nonlocal Kramers-Moyal formulas and data-driven discovery of stochastic dynamical systems with multiplicative Lévy noise
Yang Li, Jinqiao Duan
Traditional data-driven methods, effective for deterministic systems or stochastic differential equations (SDEs) with Gaussian noise, fail to handle the discontinuous sample paths…
The origin of strings and rings in the atomic dynamics of disordered systems
Omar Hussein, Yang Li, Y. Mishin
It has long been believed that the atomic dynamics in disordered structures, such as undercooled liquids and pre-melted interfaces, are characterized by collective atomic rearrange…
Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
Yubiao Yue, Minghua Jiang, Xinyue Zhang +5
Swift and accurate diagnosis for earlier-stage monkeypox (mpox) patients is crucial to avoiding its spread. However, the similarities between common skin disorders and mpox and the…
Two-Step Many-Objective Optimal Power Flow Based on Knee Point-Driven Evolutionary Algorithm
Yahui Li, Yang Li
To coordinate the economy, security and environment protection in the power system operation, a two-step many-objective optimal power flow (MaOPF) solution method is proposed. In s…
Task Expansion and Cross Refinement for Open-World Conditional Modeling
Shreyas Bhat Brahmavar, Qiyang Liu, Yang Li +1
Open-world conditional modeling (OCM), requires a single model to answer arbitrary conditional queries across heterogeneous datasets, where observed variables and targets vary and…
Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting
Siyi Liu, Yang Li, Jiang Li +2
Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods oft…
The Existence of Diagonal Quantum Latin Squares with Maximum Cardinality
Lin Huang, Yang Li
A quantum Latin square of order \(n\), denoted by \(\operatorname{QLS}(n)\), is an \(n \times n\) square whose entries are unit column vectors in the \(n\)-dimensional Hilbert spac…
LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing
Yang Li
The rapid advancement in large language models (LLMs) has brought forth a diverse range of models with varying capabilities that excel in different tasks and domains. However, sele…
Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP
Jinzuomu Zhong, Yang Li, Hui Huang +6
In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual pro…
On weak solutions to the compressible inviscid two-fluid model
Yang Li, Ewelina Zatorska
In three space dimensions, we consider the compressible inviscid model describing the time evolution of two fluids sharing the same velocity and enjoying the algebraic pressure clo…
Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion
Shanshan Zhang, Mingqian Ji, Yang Li +1
Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfacto…
Statistical Material Law Support for Room Temperature Superconductivity in the Lead Apatite System
Ning Chen, Yang Liu, Yang Li
Quantum mechanics calculations of an electronic orbital coupling distribution of the new possible Room Temperature (RT) system of lead apatite Pb10(PO4)6O system show that the comp…
Neutron Spin Resonance Near a Lifshitz Transition in Overdoped BaKFeAs
Yang Li, Dingsong Wu, Yingjie Shu +11
Elucidating the relationship between spin excitations and fermiology is essential for clarifying the pairing mechanism in iron-based superconductors (FeSCs). Here, we report inelas…
Twist-angle dependence of the proximity spin-orbit coupling in graphene on transition-metal dichalcogenides
Yang Li, Mikito Koshino
We theoretically study the proximity spin-orbit coupling in graphene on transition-metal dichalcogenides monolayer stacked with arbitrary twist angles. We find that the relative ro…
Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient
Yang Li, Feifei Zhao, Dongcheng Zhao +1
Brain-inspired Spiking Neural Networks (SNNs) have attracted much attention due to their event-based computing and energy-efficient features. However, the spiking all-or-none natur…
A Dual-scale Lead-seperated Transformer With Lead-orthogonal Attention And Meta-information For Ecg Classification
Yang Li, Guijin Wang, Zhourui Xia +2
Auxiliary diagnosis of cardiac electrophysiological status can be obtained through the analysis of 12-lead electrocardiograms (ECGs). This work proposes a dual-scale lead-separated…
Enabling Conversational Interaction with Mobile UI using Large Language Models
Bryan Wang, Gang Li, Yang Li
Conversational agents show the promise to allow users to interact with mobile devices using language. However, to perform diverse UI tasks with natural language, developers typical…
Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment
Yilei Zeng, Jiali Duan, Yang Li +4
Human-centered AI considers human experiences with AI performance. While abundant research has been helping AI achieve superhuman performance either by fully automatic or weak supe…
Minkowski's lost legacy and hadron electromagnetism
Yang Li, Wen-bo Dong, Yi-liang Yin +2
We revisit Minkowski's lost legacy on relativistic electromagnetism in order to resolve long-standing puzzles over the charge distribution of relativistic systems like hadrons. Had…
Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss
Yang Li, Shichao Kan, Zhihai He
Existing approaches for unsupervised metric learning focus on exploring self-supervision information within the input image itself. We observe that, when analyzing images, human ey…
Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL
Yixiao Zhou, Yang Li, Dongzhou Cheng +2
Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather th…