papers

Publications (363)

cs.CR2026

UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization

Wenxuan Zeng, Chao Yang, Tianshi Xu +4

Private convolutional neural network (CNN) inference based on secure two-party computation (2PC) suffers from high communication and latency overhead, especially from convolution l…

cs.CL2025

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

DeepSeek-AI, Aixin Liu, Aoxue Mei +260

We introduce DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance. The key technical breakthroughs of DeepSeek-V3.2 ar…

cs.AI2025

LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs

Xiao Hu, Yuansheng Lian, Ke Zhang +3

This study proposes an interpretable prediction framework with literature-informed fine-tuned (LIFT) LLMs for truck driving risk prediction. The framework integrates an LLM-driven…

cs.CV2026

Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing

Shuchang Lyu, Haiquan Wen, Guangliang Cheng +5

Recent advances in reasoning language models and reinforcement learning with verifiable rewards have significantly enhanced multi-step reasoning capabilities. This progress motivat…

cond-mat.mtrl-sci2013

Effect of electrode geometry on photovoltaic performance of polymer solar cells

Meng Li, Heng Ma, Zhaokui Wang +3

This paper investigates the impact of electrode geometry on the performance of polymer solar cells (PSCs). Four types of negative electrodes with equal area (0.09 cm2) but differen…

cond-mat.mtrl-sci2022

Magnetic-field modulation of topological electronic states and emergent magneto-transport in a magnetic Weyl semimetal

Jianlei Shen, Jiacheng Gao, Changjiang Yi +16

The modulation of topological electronic states by an external magnetic field is highly desired for condensed matter physics. Schemes to achieve this have been proposed theoretical…

cs.SE2024

SoK: Detection and Repair of Accessibility Issues

Liming Nie, Hao Liu, Jing Sun +6

There is an increasing global emphasis on information accessibility, with numerous researchers actively developing automated tools to detect and repair accessibility issues, thereb…

cs.DC2026

Scalable LLM Agent Tool Access in the Cloud

Mingxin Li, Enge Song, Yueshang Zuo +27

LLM agents increasingly rely on tool calling to act on external systems, and the Model Context Protocol (MCP) has quickly become its de facto interface. Operating MCP at cloud scal…

eess.AS2025

SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding

Linye Wei, Shuzhang Zhong, Songqiang Xu +3

Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect suppor…

cs.CL2025

CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks

Meng Li, Timothy M. McPhillips, Dingmin Wang +2

Recognizing the information flows and operations comprising data science and machine learning Python notebooks is critical for evaluating, reusing, and adapting notebooks for new t…

physics.acc-ph2022

CEPC Cost Model Study and Circumference Optimization

Dou Wang, Jie Gao, Manqi Ruan +8

The CEPC is a proposed high luminosity Higgs/Z factory, with the potential to be upgraded to top factory at center-of-mass energy of 360GeV. We perform an optimization study on the…

cs.CV2021

PyTorchVideo: A Deep Learning Library for Video Understanding

Haoqi Fan, Tullie Murrell, Heng Wang +13

We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tas…

math.NA2025

Error analysis for temporal second-order finite element approximations of axisymmetric mean curvature flow of genus-1 surfaces

Meng Li, Lining Wang, Yiming Wang

Existing studies on the convergence of numerical methods for curvature flows primarily focus on first-order temporal schemes. In this paper, we establish a novel error analysis for…

cond-mat.mtrl-sci2021

2D MXenes: Visible Black but Infrared White Materials

Yang Li, Cheng Xiong, He Huang +7

Black materials with low infrared absorption/emission (or IR white) are rare in nature but highly desired in numerous areas, such as solar-thermal energy harvesting, multispectral…

cond-mat.supr-con2021

Protonation-induced discrete superconducting phases in bulk FeSe single crystals

Yan Meng, Xiangzhuo Xing, Xiaolei Yi +10

The superconducting transition temperature, , of FeSe can be significantly enhanced several-fold by applying pressure, electron doping, intercalating spacing layer, and…

cs.NI2016

Machine-to-Machine (M2M) Communications in Software-defined and Virtualized Cellular Networks

Meng Li, F. Richard Yu, Pengbo Si +3

Machine-to-machine (M2M) communications have attracted great attention from both academia and industry. In this paper, with recent advances in wireless network virtualization and s…

cs.CR2026

Personalized 3D Spatiotemporal Trajectory Privacy Protection with Differential and Distortion Geo-Perturbation

Minghui Min, Yulu Li, Gang Li +4

The rapid advancement of location-based services (LBSs) in three-dimensional (3D) domains, such as smart cities and intelligent transportation, has raised concerns over 3D spatiote…

math.ST2024

Ranking Perspective for Tree-based Methods with Applications to Symbolic Feature Selection

Hengrui Luo, Meng Li

Tree-based methods are powerful nonparametric techniques in statistics and machine learning. However, their effectiveness, particularly in finite-sample settings, is not fully unde…

cs.LG2025

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Ling Team, Bin Han, Caizhi Tang +25

In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B paramet…

cs.LG2022

SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

Xin Dong, Barbara De Salvo, Meng Li +4

We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to…

cs.CL2026

What Gets Activated: Uncovering Domain and Driver Experts in MoE Language Models

Guimin Hu, Meng Li, Qiwei Peng +3

Most interpretability work focuses on layer- or neuron-level mechanisms in Transformers, leaving expert-level behavior in MoE LLMs underexplored. Motivated by functional specializa…

nucl-th2023

Study of (3He, t) charge exchange reactions to isobaric analog states in inverse kinematics

Zhixuan He, Wenjuan Bu, Chaoyuan Xiao +4

The transition between isobaric analog states (IAS) in the (3He, t) charge exchange reaction presents a unique opportunity to access the isospin structure of the nuclei. In this st…

physics.soc-ph2015

Contagion processes on the static and activity driven coupling networks

Yanjun Lei, Xin Jiang, Quantong Guo +3

The evolution of network structure and the spreading of epidemic are common coexistent dynamical processes. In most cases, network structure is treated either static or time-varyin…

cs.LG2024

Online Learning of Multiple Tasks and Their Relationships : Testing on Spam Email Data and EEG Signals Recorded in Construction Fields

Yixin Jin, Wenjing Zhou, Meiqi Wang +3

This paper examines an online multi-task learning (OMTL) method, which processes data sequentially to predict labels across related tasks. The framework learns task weights and the…

cond-mat.mtrl-sci2025

Machine Learning Pipeline for Denoising Low Signal-To-Noise Ratio and Out-of-Distribution Transmission Electron Microscopy Datasets

Brian Lee, Meng Li, Judith C Yang +2

High-resolution transmission electron microscopy (HRTEM) is crucial for observing material's structural and morphological evolution at Angstrom scales, but the electron beam can al…

cond-mat.mtrl-sci2023

Topological Insulator VxBi1.08-xSn0.02Sb0.9Te2S as a Promising n-type Thermoelectric Material

Lei Chen, Weiyao Zhaoa, Meng Li +8

As one of the most important n-type thermoelectric (TE) materials, Bi2Te3 has been studied for decades, with efforts to enhance the thermoelectric performance based on element dopi…

math.OC2021

Network-level rhythmic control of heterogeneous automated traffic with buses

Xiangdong Chen, Xi Lin, Meng Li +1

Guaranteeing the quality of transit service is of great importance to promote the attractiveness of buses and alleviate urban traffic issues such as congestion and pollution. Emerg…

stat.ME2020

Learning Asymmetric and Local Features in Multi-Dimensional Data through Wavelets with Recursive Partitioning

Meng Li, Li Ma

Effective learning of asymmetric and local features in images and other data observed on multi-dimensional grids is a challenging objective critical for a wide range of image proce…

cs.CV2026

OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppression

Chengyan Deng, Pengbin Yu, Zhentao Chen +6

Diffusion-based real-world image super-resolution (Real-ISR) has achieved remarkable perceptual quality; however, directly super-resolving images to 4K remains limited by extreme m…

cs.AR2026

DRIFT: Harnessing Inherent Fault Tolerance for Efficient and Reliable Diffusion Model Inference

Jinqi Wen, Tong Xie, Runsheng Wang +1

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and fr…

cs.CV2019

Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images

Jiexiang Wang, Cheng Bian, Meng Li +6

Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases. However, because of…

physics.bio-ph2021

Thermodynamic properties and Hilbert space of the human brain

Dongmei Shi, Meng Li, Martin Walter +1

Any macrosystem consists of many microparticles. According to statistical physics, the macroproperties of a system are realized as the statistical average of the corresponding micr…

cs.LG2025

Initial Model Incorporation for Deep Learning FWI: Pretraining or Denormalization?

Ruihua Chen, Bangyu Wu, Meng Li +1

Subsurface property neural network reparameterized full waveform inversion (FWI) has emerged as an effective unsupervised learning framework, which can invert stably with an inaccu…

cs.AI2026

HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction

Shengxuan Qiu, Haochen Huang, Shuzhang Zhong +2

Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-exploitation trade-off. Existing…

cs.AR2024

Trinity: A General Purpose FHE Accelerator

Xianglong Deng, Shengyu Fan, Zhicheng Hu +9

In this paper, we present the first multi-modal FHE accelerator based on a unified architecture, which efficiently supports CKKS, TFHE, and their conversion scheme within a single…

eess.IV2021

A Rigid Registration Method in TEVAR

Meng Li, Changyan Lin, Heng Wu +2

Since the mapping relationship between definitized intra-interventional X-ray and undefined pre-interventional Computed Tomography(CT) is uncertain, auxiliary positioning devices o…

cs.LG2026

Symbolic Density Estimation for Discrete Distributions

Ziwen Liu, Meng Li

Discrete probability laws underpin statistical modeling, yet the catalog of interpretable distributions has expanded only gradually through centuries of case-by-case mathematical d…

cs.LG2026

Learning-based Sketches for Frequency Estimation in Data Streams without Ground Truth

Xinyu Yuan, Yan Qiao, Meng Li +4

Estimating the frequency of items on the high-volume, fast data stream has been extensively studied in many areas, such as database and network measurement. Traditional sketches pr…

cs.AR2024

Efficient yet Accurate End-to-End SC Accelerator Design

Meng Li, Yixuan Hu, Tengyu Zhang +4

Providing end-to-end stochastic computing (SC) neural network acceleration for state-of-the-art (SOTA) models has become an increasingly challenging task, requiring the pursuit of…

physics.optics2024

Temporal-Spatial Manipulation of Bi-Focal Bi-Chromatic Fields for Terahertz Radiations

Jingjing Zhao, Yizhu Zhang, Yanjun Gao +5

Mixing the fundamental () and the second harmonic (2) waves in gas phase is a widely employed technique for emitting terahertz (THz) pulses. The THz generation driven by bi…

cond-mat.mtrl-sci2015

An efficient method for performance improvement of organometal halide perovskite solar cell via external electric field

Xiu Gong, Heng Ma, Yu-Rong Jiang +3

An effective method, performed adding external electric field (EEF) on CH3NH3PbI3-xClx (OPIC) perovskite layer during the annealing process, is proposed to improve the performance…

physics.ins-det2026

Development of a dual-phase xenon time projection chamber prototype for the RELICS experiment

Lingfeng Xie, Jiajun Liu, Yifei Zhao +50

The RELICS (REactor neutrino LIquid xenon Coherent elastic Scattering) experiment aims to detect coherent elastic neutrino-nucleus scattering from reactor antineutrinos using a dua…

stat.ME2019

Function-on-Scalar Quantile Regression with Application to Mass Spectrometry Proteomics Data

Yusha Liu, Meng Li, Jeffrey S. Morris

Mass spectrometry proteomics, characterized by spiky, spatially heterogeneous functional data, can be used to identify potential cancer biomarkers. Existing mass spectrometry analy…

cs.CL2026

Efficient Document Parsing via Parallel Token Prediction

Lei Li, Ze Zhao, Meng Li +6

Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs cre…

cs.SI2021

Attributed Graph Neural Networks for Recommendation Systems on Large-Scale and Sparse Graph

Yifei Zhao, Mingdong Ou, Rongzhi Zhang +1

Link prediction in structured-data is an important problem for many applications, especially for recommendation systems. Existing methods focus on how to learn the node representat…

cs.AR2026

CREATE: Cross-Layer Resilience Characterization and Optimization for Efficient yet Reliable Embodied AI Systems

Tong Xie, Yijiahao Qi, Jinqi Wen +9

Embodied Artificial Intelligence (AI) has recently attracted significant attention as it bridges AI with the physical world. Modern embodied AI systems often combine a Large Langua…

cs.RO2026

HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation

Shuanghao Bai, Meng Li, Xinyuan Lv +14

Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making hi…

eess.IV2020

Scalable Double Regularization for 3D Nano-CT Reconstruction

Wei Tang, Meng Li

Nano-CT (computerized tomography) has emerged as a non-destructive high-resolution cross-sectional imaging technique to effectively study the sub-m pore structure of shale, whi…

cs.AR2025

ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance

Tong Xie, Jiawang Zhao, Zishen Wan +5

The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to agin…

stat.ME2018

Standardization of multivariate Gaussian mixture models and background adjustment of PET images in brain oncology

Meng Li, Armin Schwartzman

In brain oncology, it is routine to evaluate the progress or remission of the disease based on the differences between a pre-treatment and a post-treatment Positron Emission Tomogr…

cs.CV2026

Full end-to-end diagnostic workflow automation of 3D OCT via foundation model-driven AI for retinal diseases

Jinze Zhang, Jian Zhong, Li Lin +18

Optical coherence tomography (OCT) has revolutionized retinal disease diagnosis with its high-resolution and three-dimensional imaging nature, yet its full diagnostic automation in…

cs.RO2026

RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

Yixue Zhang, Kun Wu, Zhi Gao +12

The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike data collection from web in vision or language, robo…

cs.CL2025

LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design

Renjie Wei, Songqiang Xu, Linfeng Zhong +5

State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexit…

astro-ph.GA2023

Tentative detection of cyanoformamide NCCONH2 in space

Juan Li, Donghui Quan, Junzhi Wang +12

The peptide-like molecules, cyanoformamide (NCCONH2), is the cyano (CN) derivative of formamide (NH2CHO). It is known to play a role in the synthesis of nucleic acid precursors und…

cond-mat.mtrl-sci2021

Atomistic mechanisms of binary alloy surface segregation from nanoseconds to seconds using accelerated dynamics

Richard B. Garza, Jiyoung Lee, Mai H. Nguyen +6

Although the equilibrium composition of many alloy surfaces is well understood, the rate of transient surface segregation during annealing is not known, despite its crucial effect…

cs.LG2026

STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy

Hui Cheng, Jinsheng Guo, Zhenhao Weng +2

Recent research in time series forecasting frequently investigates the integration of textual and visual modalities with numerical models to better navigate non-stationary environm…

q-bio.NC2025

Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics

Jiahe Li, Xin Chen, Fanqi Shen +7

Neurological disorders pose major global health challenges, driving advances in brain signal analysis. Scalp electroencephalography (EEG) and intracranial EEG (iEEG) are widely use…

cs.RO2026

DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation

Zebin Yang, Yijiahao Qi, Tong Xie +3

Vision-Language-Action (VLA) models have shown remarkable success in robotic tasks like manipulation by fusing a language model's reasoning with a vision model's 3D understanding.…

cs.CR2026

Efficient and Privacy-Preserving Distribution Statistics Analytics on Mobile Spatial Data

Xuhao Ren, Chuan Zhang, Mingyang Zhao +3

With the rapid development of mobile computing technology, massive amounts of spatial data are continuously generated from various mobile terminals and sensing devices, such as sma…

cs.LG2024

MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers

Zebin Yang, Renze Chen, Taiqiang Wu +5

In this paper, we propose MCUBERT to enable language models like BERT on tiny microcontroller units (MCUs) through network and scheduling co-optimization. We observe the embedding…

physics.optics2015

Inversed Vernier effect based single-mode laser emission in coupled microdisks

Meng Li, Nan Zhang, Kaiyang Wang +3

Recently, on-chip single-mode laser emission has attracted considerable research attention due to its wide applications. While most of single-mode lasers in coupled microdisks or m…

cs.AR2023

READ: Reliability-Enhanced Accelerator Dataflow Optimization using Critical Input Pattern Reduction

Zuodong Zhang, Renjie Wei, Meng Li +3

With the rapid advancements of deep learning in recent years, hardware accelerators are continuously deployed in more and more safety-critical applications such as autonomous drivi…

stat.AP2022

PPA: Principal Parcellation Analysis for Brain Connectomes and Multiple Traits

Rongjie Liu, Meng Li, David B. Dunson

Our understanding of the structure of the brain and its relationships with human traits is largely determined by how we represent the structural connectome. Standard practice divid…

math.CO2019

Limits of Sums for Binomial and Eulerian Numbers and their Associated Distributions

Meng Li, Ron Goldman

We provide a unified, probabilistic approach using renewal theory to derive some novel limits of sums for the normalized binomial coefficients and for the normalized Eulerian numbe…

cs.LG2024

ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding

Shuzhang Zhong, Zebin Yang, Meng Li +3

Recent advancements in generative large language models (LLMs) have significantly boosted the performance in natural language processing tasks. However, their efficiency is hampere…

cs.CR2024

PrivCirNet: Efficient Private Inference via Block Circulant Transformation

Tianshi Xu, Lemeng Wu, Runsheng Wang +1

Homomorphic encryption (HE)-based deep neural network (DNN) inference protects data and model privacy but suffers from significant computation overhead. We observe transforming the…

cs.RO2025

CDKFormer: Contextual Deviation Knowledge-Based Transformer for Long-Tail Trajectory Prediction

Yuansheng Lian, Ke Zhang, Meng Li

Predicting the future movements of surrounding vehicles is essential for ensuring the safe operation and efficient navigation of autonomous vehicles (AVs) in urban traffic environm…

cs.DC2019

RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing

Liu Ke, Udit Gupta, Carole-Jean Wu +18

Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embed…

cs.SD2022

Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet

Haichuan Yang, Yuan Shangguan, Dilin Wang +6

From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets. To navigate the Pa…

cs.LG2021

Low-Rank+Sparse Tensor Compression for Neural Networks

Cole Hawkins, Haichuan Yang, Meng Li +2

Low-rank tensor compression has been proposed as a promising approach to reduce the memory and compute requirements of neural networks for their deployment on edge devices. Tensor…

stat.ME2023

Valid confidence intervals for regression with best subset selection

Huiming Lin, Meng Li

Classical confidence intervals after best subset selection are widely implemented in statistical software and are routinely used to guide practitioners in scientific fields to conc…

cs.CV2021

AlphaNet: Improved Training of Supernets with Alpha-Divergence

Dilin Wang, Chengyue Gong, Meng Li +2

Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles a…

math.DS2025

Periodic Points of Hamiltonian Diffeomorphisms Equal to Nondegenerate Linear Maps at Infinity

Meng Li

We study Hamiltonian diffeomorphisms on symplectic Euclidean spaces that are equal to non-degenerate linear maps at infinity. Under the assumption that there exists an isolated hom…

math.OC2023

On the Softplus Penalty for Constrained Convex Optimization

Meng Li, Paul Grigas, Alper Atamturk

We study a new penalty reformulation of constrained convex optimization based on the softplus penalty function. We develop novel and tight upper bounds on the objective value gap a…

cs.LG2024

Real-Time Summarization of Twitter

Yixin Jin, Meiqi Wang, Meng Li +3

In this paper, we describe our approaches to TREC Real-Time Summarization of Twitter. We focus on real time push notification scenario, which requires a system monitors the stream…

cs.LG2024

AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference

Shuzhang Zhong, Ling Liang, Yuan Wang +3

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their d…

cs.CV2025

Deep Learning Based Domain Adaptation Methods in Remote Sensing: A Comprehensive Survey

Shuchang Lyu, Qi Zhao, Zheng Zhou +6

Domain adaptation is a crucial and increasingly important task in remote sensing, aiming to transfer knowledge from a source domain a differently distributed target domain. It has…

cs.CV2021

Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation

Jiaqi Gu, Hyoukjun Kwon, Dilin Wang +6

Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly des…

stat.ME2022

Inference in Functional Linear Quantile Regression

Meng Li, Kehui Wang, Arnab Maity +1

In this paper, we study statistical inference in functional quantile regression for scalar response and a functional covariate. Specifically, we consider a functional linear quanti…

cs.CR2026

Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks

Yi Yang, Xiaoke Chen, Jinyang Huang +6

Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few…

cs.AR2025

SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding

Linfeng Zhong, Songqiang Xu, Huifeng Wen +4

The growing demand for efficient long-sequence modeling on edge devices has propelled widespread adoption of State Space Models (SSMs) like Mamba, due to their superior computation…

cs.LG2022

Decentralized Unsupervised Learning of Visual Representations

Yawen Wu, Zhepeng Wang, Dewen Zeng +3

Collaborative learning enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing collaborative lear…

cs.AI2020

NASGEM: Neural Architecture Search via Graph Embedding Method

Hsin-Pai Cheng, Tunhou Zhang, Yixing Zhang +7

Neural Architecture Search (NAS) automates and prospers the design of neural networks. Estimator-based NAS has been proposed recently to model the relationship between architecture…

cs.RO2026

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

Yifei Su, Ning Liu, Dong Chen +6

Generative modeling-based visuomotor policies have been widely adopted in robotic manipulation, attributed to their ability to model multimodal action distributions. However, the h…

cs.CV2018

Computed Tomography Image Enhancement using 3D Convolutional Neural Network

Meng Li, Shiwen Shen, Wen Gao +2

Computed tomography (CT) is increasingly being used for cancer screening, such as early detection of lung cancer. However, CT studies have varying pixel spacing due to differences…

cs.LG2022

BiT: Robustly Binarized Multi-distilled Transformer

Zechun Liu, Barlas Oguz, Aasish Pappu +5

Modern pre-trained transformers have rapidly advanced the state-of-the-art in machine learning, but have also grown in parameters and computational complexity, making them increasi…

q-bio.NC2026

Towards unified brain-to-text decoding across speech production and perception

Zhizhang Yuan, Yang Yang, Gaorui Zhang +7

Speech production and perception are the main ways humans communicate daily. Prior brain-to-text decoding studies have largely focused on a single modality and alphabetic languages…

cs.CV2025

UltraSeP: Sequence-aware Pre-training for Echocardiography Probe Movement Guidance

Haojun Jiang, Teng Wang, Zhenguo Sun +8

Echocardiography is an essential medical technique for diagnosing cardiovascular diseases, but its high operational complexity has led to a shortage of trained professionals. To ad…

astro-ph.GA2021

Propionamide (C2H5CONH2): The largest peptide-like molecule in space

Juan Li, Junzhi Wang, Xing Lu +16

Peptide bonds, as the molecular bridges that connect amino acids, are crucial to the formation of proteins. Searches and studies of molecules with embedded peptide-like bonds are t…

cond-mat.mtrl-sci2023

Infrared anomalies in ultrathin Ti3C2Tx MXene films

Meng Li, Tao Cheng, Gongze Liu +5

Visible transparent but infrared reflective materials are ideal candidates for both transparent conductive films and low-emissivity glass, which are highly desired in a broad varie…

cs.CR2023

Decentralized Threshold Signatures with Dynamically Private Accountability

Meng Li, Mingwei Zhang, Qing Wang +5

Threshold signatures are a fundamental cryptographic primitive used in many practical applications. As proposed by Boneh and Komlo (CRYPTO'22), TAPS is a threshold signature that i…

cond-mat.mtrl-sci2024

Ubiquitous short-range order in multi-principal element alloys

Ying Han, Hangman Chen, Yongwen Sun +10

Recent research in multi-principal element alloys (MPEAs) has increasingly focused on the exploration and exploitation of short-range order (SRO) to enhance material performance. H…

hep-ex2024

Reactor neutrino liquid xenon coherent elastic scattering experiment

Chang Cai, Guocai Chen, Jiangyu Chen +46

Coherent elastic neutrino-nucleus scattering (CEvNS) provides a unique probe for neutrino properties Beyond the Standard Model (BSM) physics. REactor neutrino LIquid xenon Coherent…

cond-mat.supr-con2016

Superfluid density and microwave conductivity of FeSe superconductor: ultra-long-lived quasiparticles and extended s-wave energy gap

Meng Li, N. R. Lee-Hone, Shun Chi +5

FeSe is an iron-based superconductor of immense current interest due to the large enhancements of Tc that occur when it is pressurized or grown as a single layer on an insulating s…

eess.SY2020

Simulation Comparisons of Vehicle-based and Phase-based Traffic Control for Autonomous Vehicles at Isolated Intersections

Chen Yang, Xi Lin, Meng Li +1

With the advent of autonomous driving technologies, traffic control at intersections is expected to experience revolutionary changes. Various novel intersection control methods hav…

cs.RO2024

VascularPilot3D: Toward a 3D fully autonomous navigation for endovascular robotics

Jingwei Song, Keke Yang, Han Chen +8

This research reports VascularPilot3D, the first 3D fully autonomous endovascular robot navigation system. As an exploration toward autonomous guidewire navigation, VascularPilot3D…

eess.IV2023

TransCC: Transformer Network for Coronary Artery CCTA Segmentation

Chenchu Xu, Meng Li, Xue Wu

The accurate segmentation of Coronary Computed Tomography Angiography (CCTA) images holds substantial clinical value for the early detection and treatment of Coronary Heart Disease…

cs.CG2018

Streaming Algorithms for Planar Convex Hulls

Martin Farach-Colton, Meng Li, Meng-Tsung Tsai

Many classical algorithms are known for computing the convex hull of a set of point in using space. For large point sets, whose size exceeds the size of t…

cs.CL2025

Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization

Meng Li, Guangda Huzhang, Haibo Zhang +2

Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood…

cs.LG2018

Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism

Zhengchao Zhang, Meng Li, Xi Lin +2

Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynami…