Publications (363)
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction
Zerong Zheng, Tao Yu, Yebin Liu +1
Modeling 3D humans accurately and robustly from a single image is very challenging, and the key for such an ill-posed problem is the 3D representation of the human models. To overc…
MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond
Shenghao Ren, Yi Lu, Jiayi Huang +5
Existing human Motion Capture (MoCap) methods mostly focus on the visual similarity while neglecting the physical plausibility. As a result, downstream tasks such as driving virtua…
HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models
Mengcheng Li, Hongwen Zhang, Yuxiang Zhang +3
Recent years have witnessed a trend of the deep integration of the generation and reconstruction paradigms. In this paper, we extend the ability of controllable generative models f…
Non-Hermitian coherent coupling of nanomagnets by exchange spin waves
Hanchen Wang, Jilei Chen, Tao Yu +16
Non-Hermitian physics has recently attracted much attention in optics and photonics. Less explored is non-Hermitian magnonics that provides opportunities to take advantage of the i…
Kwai Keye-VL Technical Report
Kwai Keye Team, Biao Yang, Bin Wen +57
While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form vi…
Random Laplacian Features for Learning with Hyperbolic Space
Tao Yu, Christopher De Sa
Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been develope…
Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
Haolin Song, Hongbo Zhu, Tao Yu +5
For full-size humanoid robots, even with recent advances in reinforcement learning-based control, achieving reliable locomotion on complex terrains, such as long staircases, remain…
Atomic decoration for improving the efficiency of field electron emission of carbon nanotubes
Guihua Chen, Zhibing Li, Jie Peng +9
The field electron emission from the single-walled carbon nanotubes with their open ends terminated by -BH, -NH, and -O has been simulated. The apex-vacuum barrier and the emission…
Qwen-CUA: Native Computer Use for (almost) Everything
Dunjie Lu, Shuai Bai, Tianyi Bai +42
Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive expe…
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Tianbao Xie, Danyang Zhang, Jixuan Chen +14
Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing access…
Audio Matters Too! Enhancing Markerless Motion Capture with Audio Signals for String Performance Capture
Yitong Jin, Zhiping Qiu, Yi Shi +10
In this paper, we touch on the problem of markerless multi-modal human motion capture especially for string performance capture which involves inherently subtle hand-string contact…
DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor
Tao Yu, Zerong Zheng, Kaiwen Guo +5
We propose DoubleFusion, a new real-time system that combines volumetric dynamic reconstruction with data-driven template fitting to simultaneously reconstruct detailed geometry, n…
PARF: Primitive-Aware Radiance Fusion for Indoor Scene Novel View Synthesis
Haiyang Ying, Baowei Jiang, Jinzhi Zhang +4
This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality. The key idea is t…
Pumping of spin supercurrent in unitary triplet superconductors
Ping Li, Tao Yu
One efficient mechanism for generating a charge supercurrent is Andreev reflection, in which the electric current injected from a normal metal into a conventional superconductor is…
Shadow Cones: A Generalized Framework for Partial Order Embeddings
Tao Yu, Toni J. B. Liu, Albert Tseng +1
Hyperbolic space has proven to be well-suited for capturing hierarchical relations in data, such as trees and directed acyclic graphs. Prior work introduced the concept of entailme…
StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video
Lizhen Wang, Xiaochen Zhao, Jingxiang Sun +4
Face reenactment methods attempt to restore and re-animate portrait videos as realistically as possible. Existing methods face a dilemma in quality versus controllability: 2D GAN-b…
Curvature-based Comparison of Two Neural Networks
Tao Yu, Huan Long, John E. Hopcroft
In this paper we show the similarities and differences of two deep neural networks by comparing the manifolds composed of activation vectors in each fully connected layer of them.…
Localized Orthogonal Decomposition Method with Interpolation for Multiscale Elliptic Problem
Tao Yu, Xingye Yue
This paper employs a localized orthogonal decomposition (LOD) method with interpolation for solving the multiscale elliptic problem. This method does not need any assumptions…
Digital Twin-Enabled Blockage-Aware Dynamic mmWave Multi-Hop V2X Communication
Supat Roongpraiwan, Zongdian Li, Tao Yu +1
Millimeter wave (mmWave) technology in vehicle-to-everything (V2X) communication offers unprecedented data rates and low latency, but faces significant reliability challenges due t…
Hybrid AHS: A Hybrid of Kalman Filter and Deep Learning for Acoustic Howling Suppression
Hao Zhang, Meng Yu, Yuzhong Wu +2
Deep learning has been recently introduced for efficient acoustic howling suppression (AHS). However, the recurrent nature of howling creates a mismatch between offline training an…
Asymptotic Uncertainty of False Discovery Proportion
Meng Mei, Tao Yu, Yuan Jiang
Multiple testing has been a popular topic in statistical research. Although vast works have been done, controlling the false discoveries remains a challenging task when the corresp…
OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation
Peng Li, Jiayin Zhao, Jingyao Wu +3
Light field disparity estimation is an essential task in computer vision with various applications. Although supervised learning-based methods have achieved both higher accuracy an…
Lower and Upper Bounds for Positive Bases of Skein Algebras
Thang T. Q. Lê, Dylan P. Thurston, Tao Yu
We show that the if a sequence of normalized polynomials gives rise to a positive basis of the skein algebra of a surface, then it is sandwiched between the two types of Chebyshev…
Maximum profile binomial likelihood estimation for the semiparametric Box--Cox power transformation model
Pengfei Li, Tao Yu, Baojiang Chen +1
The Box--Cox transformation model has been widely applied for many years. The parametric version of this model assumes that the random error follows a parametric distribution, say…
Left-invariant Ricci collineations associated to Yano connections on three-dimensional Lorentzian Lie groups
Tao Yu
In this paper, we classify Left-invariant Ricci collineations associated to Yano connections on three-dimensional Lorentzian Lie groups.
Progressive Image Inpainting with Full-Resolution Residual Network
Zongyu Guo, Zhibo Chen, Tao Yu +2
Recently, learning-based algorithms for image inpainting achieve remarkable progress dealing with squared or irregular holes. However, they fail to generate plausible textures insi…
Momentum Approximation in Asynchronous Private Federated Learning
Tao Yu, Congzheng Song, Jianyu Wang +1
Asynchronous protocols have been shown to improve the scalability of federated learning (FL) with a massive number of clients. Meanwhile, momentum-based methods can achieve the bes…
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
Yuhang Lai, Chengxi Li, Yiming Wang +7
We introduce DS-1000, a code generation benchmark with a thousand data science problems spanning seven Python libraries, such as NumPy and Pandas. Compared to prior works, DS-1000…
A Quantum trace map for 3-manifolds
Stavros Garoufalidis, Tao Yu
We define a quantum trace map from the skein module of a 3-manifold with torus boundary components to a module (left and right quotient of a quantum torus) constructed from an idea…
Unveiling a Pump-Induced Magnon Mode via its Strong Interaction with Walker Modes
J. W. Rao, Bimu Yao, C. Y. Wang +3
We observe a power-dependent anticrossing of Walker spin-wave modes under microwave pumping when a ferrimagnet is placed in a microwave waveguide that does not support any discrete…
Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search
Tao Yu, yiming ding, Shenghua Chai +16
Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively…
KnobCF: Uncertainty-aware Knob Tuning
Yu Yan, Junfang Huang, Hongzhi Wang +3
The knob tuning aims to optimize database performance by searching for the most effective knob configuration under a certain workload. Existing works suffer two significant problem…
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
Naihao Deng, Shuaichen Chang, Peng Shi +2
Existing text-to-SQL research only considers complete questions as the input, but lay-users might strive to formulate a complete question. To build a smarter natural language inter…
The equivalence of precompactness, zero maximal pattern entropy and bounded mean complexity for finite partitions
Jian Li, Tao Yu, Xianliang Zhong
In this paper, we investigate several types of low complexity of finite partitions, including precompactness, zero maximal pattern entropy, bounded mean complexity and mean equicon…
Spin Quenching and Transport by Hidden Dzyaloshinskii-Moriya Interactions
Xiyin Ye, Qirui Cui, Weiwei Lin +1
Explicit interactions, \textit{e.g.}, dipolar and exchange couplings, usually govern magnetization dynamics. Some interactions may be hidden from the global crystal symmetry. We re…
Proposal of Readout Electronics for CSNS-WNS BaF2 Detector
Deliang Zhang, Ping Cao, Qi Wang +5
BaF2 (Barium fluoride) detector is one of the experiment facilities at the under construction CSNS-WNS (White Neutron Source at China Spallation Neutron Source). It is designed for…
LIT-GS: LiDAR-Inertial-Thermal Gaussian Splatting for Illumination-Robust Mapping
Shikuan Shi, Chunran Zheng, Jiaming Xu +3
Gaussian Splatting has enabled real-time neural rendering, yet existing LiDAR-inertial-visual (LIV) Gaussian mapping pipelines remain fragile under illumination changes and texture…
Internet of Federated Digital Twins (IoFDT): Connecting Twins Beyond Borders for Society 5.0
Tao Yu, Zongdian Li, Kei Sakaguchi +3
The concept of digital twin (DT), which enables the creation of a programmable, digital representation of physical systems, is expected to revolutionize future industries and will…
Maximum smoothed likelihood method for the combination of multiple diagnostic tests, with application to the ROC estimation
Fangyong Zheng, Pengfei Li, Tao Yu
In medical diagnostics, leveraging multiple biomarkers can significantly improve classification accuracy compared to using a single biomarker. While existing methods based on expon…
Chiral Locking of Magnon Flow and Electron Spin Accumulation in Their Near-Field Radiative Spin Transfer
Xi-Han Zhou, Xiyin Ye, Tao Yu
We report a non-contact mechanism for directional injection of magnons in magnetic films when driven by a spin accumulation of electrons of a nearby metallic layer, gove…
Chiral excitation of spin waves in ferromagnetic films
Tao Yu, Chuanpu Liu, Haiming Yu +2
We theoretically investigate the interlayer dipolar and exchange couplings for an array of metallic magnetic nanowires grown on top of an extended ultrathin yttrium iron garnet fil…
Performance Evaluation for LTE-V based Vehicle-to-Vehicle Platooning Communication
Tao Yu, Shunqing Zhang, Shan Cao +1
With the raising demand for autonomous driving, vehicle-to-vehicle communications becomes a key technology enabler for the future intelligent transportation system. Based on our cu…
ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
Yongqi An, Chang Lu, Kuan Zhu +5
Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences.…
MulayCap: Multi-layer Human Performance Capture Using A Monocular Video Camera
Zhaoqi Su, Weilin Wan, Tao Yu +4
We introduce MulayCap, a novel human performance capture method using a monocular video camera without the need for pre-scanning. The method uses "multi-layer" representations for…
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
Zhiqing Cui, Haotong Xie, Jiahao Yuan +11
Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so decom…
IREE Oriented Active RIS-Assisted Green communication System with Outdated CSI
Kai Cao, Tao Yu, Jihong Li +5
The rapid evolution of communication technologies has spurred a growing demand for energy-efficient network architectures and performance metrics. Active Reconfigurable Intelligent…
Measure-theoretic mean equicontinuity and bounded complexity
Tao Yu
Let be a measure preserving system. We say that a function is -mean equicontinuous if for any there is and meas…
Lemur: Harmonizing Natural Language and Code for Language Agents
Yiheng Xu, Hongjin Su, Chen Xing +13
We introduce Lemur and Lemur-Chat, openly accessible language models optimized for both natural language and coding capabilities to serve as the backbone of versatile language agen…
Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
Fangyu Lei, Jixuan Chen, Yuxiao Ye +13
Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operati…
SummerTime: Text Summarization Toolkit for Non-experts
Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma +5
Recent advances in summarization provide models that can generate summaries of higher quality. Such models now exist for a number of summarization tasks, including query-based summ…
Sequence entropy tuples and mean sensitive tuples
Jie Li, Chunlin Liu, Siming Tu +1
Using the idea of local entropy theory, we characterize the sequence entropy tuple via mean forms of the sensitive tuple in both topological and measure-theoretical senses. For the…
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
Tao Yu, Chien-Sheng Wu, Xi Victoria Lin +6
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data…
Training LLMs with MXFP4
Albert Tseng, Tao Yu, Youngsuk Park
Low precision (LP) datatypes such as MXFP4 can accelerate matrix multiplications (GEMMs) and reduce training costs. However, directly using MXFP4 instead of BF16 during training si…
Fluctuation-based Adaptive Structured Pruning for Large Language Models
Yongqi An, Xu Zhao, Tao Yu +2
Network Pruning is a promising way to address the huge computing resource demands of the deployment and inference of Large Language Models (LLMs). Retraining-free is important for…
Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation
Yuxuan Zhou, Tao Yu, Wen Huang +3
The generalization capability of deepfake detectors is critical for real-world use. Data augmentation via synthetic fake face generation effectively enhances generalization, yet cu…
Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
Tianbao Xie, Siheng Zhao, Chen Henry Wu +5
Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To a…
Coneheads: Hierarchy Aware Attention
Albert Tseng, Tao Yu, Toni J. B. Liu +1
Attention networks such as transformers have achieved state-of-the-art performance in many domains. These networks rely heavily on the dot product attention operator, which compute…
Non-Relativistic Spin-Orbit Interaction in Triplet Superconductors: Edelstein Effect and Spin Pumping by Electric Fields
Ping Li, G. A. Bobkov, I. V. Bobkova +1
Non-relativistic momentum-dependent spin splitting, as observed in collinear altermagnets and non-collinear -wave magnets, provides exciting avenues for controlling spin dynamic…
Explicit representations and Azumaya loci of skein algebras of small surfaces
Tao Yu
We construct finite dimensional representations of the Kauffman bracket skein algebra of the one-punctured torus and four-punctured sphere at all roots of unity. The representation…
Square-free Discriminants of Matrices and the Generalized Spectral Characterizations of Graphs
Wei Wang, Tao Yu
Let and denote the set of all symmetric matrices over the ring of integers and the set of all orthogonal ma…
MuonBP: Faster Muon via Block-Periodic Orthogonalization
Ahmed Khaled, Kaan Ozkara, Tao Yu +2
Gradient orthogonalization is a simple strategy that shows great utility in speeding up gradient descent. The Muon optimizer (Jordan, Jin, et al., 2024) combines gradient orthogona…
ImmersiveNeRF: Hybrid Radiance Fields for Unbounded Immersive Light Field Reconstruction
Xiaohang Yu, Haoxiang Wang, Yuqi Han +3
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolatio…
A Model-Data Dual-Driven Resource Allocation Scheme for IREE Oriented 6G Networks
Tao Yu, Simin Wang, Shunqing Zhang +6
The rapid and substantial fluctuations in wireless network capacity and traffic demand, driven by the emergence of 6G technologies, have exacerbated the issue of traffic-capacity m…
Giant oscillatory Gilbert damping in superconductor/ferromagnet/superconductor junctions
Yunyan Yao, Ranran Cai, Tao Yu +6
Interfaces between materials with differently ordered phases present unique opportunities for exotic physical properties, especially the interplay between ferromagnetism and superc…
How Roadside Units Enhance Intersection Safety? Cooperative Autonomous Driving System Design and A Proof of Concept
Taoyuan Yu, Kui Wang, Zongdian Li +3
Intersections remain one of the most hazardous locations in urban road networks, where heterogeneous traffic participants and limited visibility frequently lead to severe traffic c…
Image of the time-dependent black hole
Yu Liang, Sen Guo, Kai Lin +3
The Event Horizon Telescope's 2024 observations report a shift in the position angle of the brightness asymmetry in M87*, revealing time variability in the black hole's image. In t…
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Zhiyong Wu, Chengcheng Han, Zichen Ding +5
Autonomous interaction with the computer has been a longstanding challenge with great potential, and the recent proliferation of large language models (LLMs) has markedly accelerat…
PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
Peng Li, Wangguandong Zheng, Yuan Liu +9
Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, full-body reconstruction from a monocular RGB image r…
Region Normalization for Image Inpainting
Tao Yu, Zongyu Guo, Xin Jin +5
Feature Normalization (FN) is an important technique to help neural network training, which typically normalizes features across spatial dimensions. Most previous image inpainting…
ProbNVS: Fast Novel View Synthesis with Learned Probability-Guided Sampling
Yuemei Zhou, Tao Yu, Zerong Zheng +2
Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which…
Efficient Gating of Magnons by Proximity Superconductors
Tao Yu, Gerrit E. W. Bauer
Electrostatic gating confines and controls the transport of electrons in integrated circuits. Magnons, the quanta of spin waves of the magnetic order, are promising alternative inf…
QED theory of electron beam-induced electronic excitation and its effect on sputtering cross sections in 2D crystals
Anthony Yoshimura, Michael Lamparski, Joel Giedt +6
Many computational models have been developed to predict the rates of atomic displacements in two-dimensional (2D) materials under electron beam irradiation. However, these models…
Distributed Networked Controller Design for Large-scale Systems under Round-Robin Communication Protocol
Tao Yu, Junlin Xiong
This paper studies the distributed L2-gain control problem for continuous-time large-scale systems under Round-Robin communication protocol. In this protocol, each sub-controller o…
Efficient Spin Seebeck and Spin Nernst Effects of Magnons in Altermagnets
Qirui Cui, Bowen Zeng, Tao Yu +2
We report two non-degenerate magnon modes with opposite spins or chiralities in collinearly antiferromagnetic insulators driven by symmetry-governed anisotropic exchange couplings.…
Transverse and Unidirectional Spin Pumping
Ping Li, Chengyuan Cai, Tao Yu
Conventional spin pumping, driven by magnetization dynamics, is longitudinal since the pumped spin current flows normal to the interface between the ferromagnet and the conductor.…
Automated Self-Supervised Learning for Recommendation
Lianghao Xia, Chao Huang, Chunzhen Huang +3
Graph neural networks (GNNs) have emerged as the state-of-the-art paradigm for collaborative filtering (CF). To improve the representation quality over limited labeled data, contra…
AutoDroid: LLM-powered Task Automation in Android
Hao Wen, Yuanchun Li, Guohong Liu +7
Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalab…
ImViD: Immersive Volumetric Videos for Enhanced VR Engagement
Zhengxian Yang, Shi Pan, Shengqi Wang +7
User engagement is greatly enhanced by fully immersive multi-modal experiences that combine visual and auditory stimuli. Consequently, the next frontier in VR/AR technologies lies…
FOLIO: Natural Language Reasoning with First-Order Logic
Simeng Han, Hailey Schoelkopf, Yilun Zhao +32
Large language models (LLMs) have achieved remarkable performance on a variety of natural language understanding tasks. However, existing benchmarks are inadequate in measuring the…
DC-SPP-YOLO: Dense Connection and Spatial Pyramid Pooling Based YOLO for Object Detection
Zhanchao Huang, Jianlin Wang, Xuesong Fu +3
Although the YOLOv2 method is extremely fast on object detection, its detection accuracy is restricted due to the low performance of its backbone network and the underutilization o…
Receiver operating characteristic curve analysis with non-ignorable missing disease status
Dingding Hu, Tao Yu, Pengfei Li
This article considers the receiver operating characteristic (ROC) curve analysis for medical data with non-ignorable missingness in the disease status. In the framework of the log…
Chiral Coupling to Magnetodipolar Radiation
Tao Yu, Gerrit E. W. Bauer
We review and extend the theory of chiral pumping of spin waves by magnetodipolar stray fields that generate unidirectional spin currents and asymmetric magnon densities. We illust…
GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration
Yuchen Sun, Shanhui Zhao, Tao Yu +5
GUI agents hold significant potential to enhance the experience and efficiency of human-device interaction. However, current methods face challenges in generalizing across applicat…
MKEvolve: A Modular Multi-Agent Framework for Kernel Code Generation
Jason Yoo, Rajarshi Saha, Shaowei Zhu +3
Despite rapid progress in LLM-based code generation, writing correct and performant kernels for hardware accelerators remains a key bottleneck in scaling modern ML workloads. We pr…
Local Patch AutoAugment with Multi-Agent Collaboration
Shiqi Lin, Tao Yu, Ruoyu Feng +3
Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieve…
Digital Twin-Empowered Cooperative Autonomous Car-sharing Services: Proof-of-Concept
Kazuma Nonomura, Kui Wang, Zongdian Li +2
This paper presents a digital twin-empowered real-time optimal delivery system specifically validated through a proof-of-concept (PoC) demonstration of a real-world autonomous car-…
Test for homogeneity with unordered paired observations
Jiahua Chen, Pengfei Li, Jing Qin +1
In some applications, an experimental unit is composed of two distinct but related subunits. The response from such a unit is but we observe only $Y_1 = \min\{X_{1…
Green Wireless Network Scaling for Joint Deployment: Multi-BSs or Multi-RISs?
Tao Yu, Simin Wang, Shunqing Zhang +6
The imminent emergence of sixth-generation (6G) networks faces critical challenges from spatially heterogeneous traffic and escalating energy consumption, necessitating sustainable…
Persistent nodal magnon-photon polariton in ferromagnetic heterostructures
Zhuolun Qiu, Xi-Han Zhou, Hanchen Wang +2
Exceptional points with coalescence of eigenvalues and eigenvectors are spectral singularities in the parameter space, achieving which often needs fine-tuning of parameters in quan…
OpenAgents: An Open Platform for Language Agents in the Wild
Tianbao Xie, Fan Zhou, Zhoujun Cheng +13
Language agents show potential in being capable of utilizing natural language for varied and intricate tasks in diverse environments, particularly when built upon large language mo…
LaPA: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation
Jiabing Yang, Yixiang Chen, Zichen Wen +8
Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while effective in short sequences, the…
ELGAR: Expressive Cello Performance Motion Generation for Audio Rendition
Zhiping Qiu, Yitong Jin, Yuan Wang +7
The art of instrument performance stands as a vivid manifestation of human creativity and emotion. Nonetheless, generating instrument performance motions is a highly challenging ta…
Surface Ferron Excitations in Ferroelectrics and Their Directional Routing
Xi-Han Zhou, Chengyuan Cai, Ping Tang +4
The duality between the electric and magnetic dipoles inspires recent comparisons between ferronics and magnonics. Here we predict surface polarization waves or ``ferrons" in ferro…
Roadside Units Assisted Localized Automated Vehicle Maneuvering: An Offline Reinforcement Learning Approach
Kui Wang, Changyang She, Zongdian Li +3
Traffic intersections present significant challenges for the safe and efficient maneuvering of connected and automated vehicles (CAVs). This research proposes an innovative roadsid…
Interaction-Induced Dimensional Crossover through Full 3D to 1D
Tao Yu, Xiaoran Ye, Zhaoxin Liang
The exploration of dimensional crossover carries profound fundamental significance, serving as a crucial bridge in comprehending the remarkable disparities observed in transitional…
Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation
Jiabing Yang, Yixiang Chen, Yuan Xu +6
Preference over model-generated emotion descriptions is emerging as a standard evaluation metric for multimodal emotion understanding, exemplified by the MER2026 MER-Prefer track o…
Left-invariant Ricci collineations associated to canonical connections on three-dimensional Lorentzian Lie groups
Tao Yu
In this paper, we classify Left-invariant Ricci collineations associated to canonical connections and Kobayashi-Nomizu connections on three-dimensional Lorentzian Lie groups.
IREE Oriented Green 6G Networks: A Radial Basis Function Based Approach
Tao Yu, Pengbo Huang, Shunqing Zhang +3
In order to provide design guidelines for energy efficient 6G networks, we propose a novel radial basis function (RBF) based optimization framework to maximize the integrated relat…
Salvaging Federated Learning by Local Adaptation
Tao Yu, Eugene Bagdasaryan, Vitaly Shmatikov
Federated learning (FL) is a heavily promoted approach for training ML models on sensitive data, e.g., text typed by users on their smartphones. FL is expressly designed for traini…
Augmented Intelligence in Smart Intersections: Local Digital Twins-Assisted Hybrid Autonomous Driving
Kui Wang, Kazuma Nonomura, Zongdian Li +6
Vehicle-road collaboration is a promising approach for enhancing the safety and efficiency of autonomous driving by extending the intelligence of onboard systems to smart roadside…