Publications (36)
Non-Lambertian Surface Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field
Mingyuan Zhou, Yu Ji, Yuqi Ding +3
Recovering the shape and reflectance of non-Lambertian surfaces remains a challenging problem in computer vision since the view-dependent appearance invalidates traditional photo-c…
Electronic states and magnetic response of MnBi2Te4 by scanning tunneling microscopy and spectroscopy
Yonghao Yuan, Xintong Wang, Hao Li +10
Exotic quantum phenomena have been demonstrated in recently discovered intrinsic magnetic topological insulator MnBi2Te4. At its two-dimensional limit, quantum anomalous Hall (QAH)…
FPSA: A Full System Stack Solution for Reconfigurable ReRAM-based NN Accelerator Architecture
Yu Ji, Youyang Zhang, Xinfeng Xie +5
Neural Network (NN) accelerators with emerging ReRAM (resistive random access memory) technologies have been investigated as one of the promising solutions to address the \textit{m…
DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation
Jiayi Chen, Wen Wu, Liye Shi +4
Sequential recommendations have made great strides in accurately predicting the future behavior of users. However, seeking accuracy alone may bring side effects such as unfair and…
Crossbar-aware neural network pruning
Ling Liang, Lei Deng, Yueling Zeng +5
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operati…
Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design
Wenxin Wang, Yule Hou, Yu Ji +2
Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads. We identify…
Development of a quadripartite wakefield structure as dechirper for free electron laser
Yu Ji, Congrui Lei, Jiahang Shao +13
Wakefield structures are critical for beam manipulation in free-electron lasers (FELs), particularly when serving as dechirpers, where beam-induced longitudinal wakefields compensa…
DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation
Chen Xu, Tian Lan, Yu Ji +8
Constrained decoding approaches aim to control the meaning or style of text generated by the pre-trained large language models (LLMs or also PLMs) for various tasks at inference ti…
Tunable magnetism and electron correlation in Titanium-based Kagome metals RETi3Bi4 (RE = Yb, Pr, and Nd) by rare-earth engineering
Long Chen, Ying Zhou, He Zhang +10
Rare-earth engineering is an effective way to introduce and tune the magnetism in topological Kagome magnets, which has been acting as a fertile platform to investigate the quantum…
Towards Multi-Subsession Conversational Recommendation
Yu Ji, Qi Shen, Shixuan Zhu +4
Conversational recommendation systems (CRS) could acquire dynamic user preferences towards desired items through multi-round interactive dialogue. Previous CRS mainly focuses on th…
Anomalous doping evolution of superconductivity and quasiparticle interference in Bi2Sr2Ca2Cu3O10+δ trilayer cuprates
Zhenqi Hao, Changwei Zou, Xiangyu Luo +6
We use scanning tunneling microscopy to investigate Bi2Sr2Ca2Cu3O10+δ trilayer cuprates from the optimally doped to overdoped regime. We find that the two distinct superconducting…
Metacognition-Enhanced Few-Shot Prompting With Positive Reinforcement
Yu Ji, Wen Wu, Yi Hu +2
Few-shot prompting elicits the remarkable abilities of large language models by equipping them with a few demonstration examples in the input. However, the traditional method of pr…
Robust 3D Human Motion Reconstruction Via Dynamic Template Construction
Zhong Li, Yu Ji, Wei Yang +2
In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc…
Textureless Deformable Surface Reconstruction with Invisible Markers
Xinyuan Li, Yu Guo, Yubei Tu +4
Reconstructing and tracking deformable surface with little or no texture has posed long-standing challenges. Fundamentally, the challenges stem from textureless surfaces lacking fe…
Is ChatGPT a Good Personality Recognizer? A Preliminary Study
Yu Ji, Wen Wu, Hong Zheng +3
In recent years, personality has been regarded as a valuable personal factor being incorporated into numerous tasks such as sentiment analysis and product recommendation. This has…
The emergence of global phase coherence from local pairing in underdoped cuprates
Shusen Ye, Changwei Zou, Hongtao Yan +6
In conventional metal superconductors such as aluminum, the large number of weakly bounded Cooper pairs become phase coherent as soon as they start to form. The cuprate high critic…
Rippled graphene pores as fluidic memristive devices with synaptic and neuromorphic functionalities
Wenzhe Zhou, Dongjiao Ge, Ao Zhang +8
Nanofluidic memristive devices work with nanoscale pores and ions dissolved in water, which harness the ionic memory effect aiming to store and process information. These devices s…
Light Field-Based Underwater 3D Reconstruction Via Angular Resampling
Yuqi Ding, Zhang Chen, Yu Ji +2
Recovering 3D geometry of underwater scenes is challenging because of non-linear refraction of light at the water-air interface caused by the camera housing. We present a light fie…
Think Before You Act: Intention-Guided Reasoning for LLM-Based Location Prediction
Qingxiang Liu, Anqi Liang, Zhuoyang Jiang +5
Predicting a user's next Point-of-Interest (POI) based on their historical check-in records is a fundamental task in location-based services. While recent methods incorporating lar…
Tinkering Against Scaling
Bolun Zhang, Yang Shen, Linzhuo Li +4
The ascent of scaling in artificial intelligence research has revolutionized the field over the past decade, yet it presents significant challenges for academic researchers, partic…
Generating axial magnetic fields via two plasmon decay driven by a twisted laser
Yu Ji, Chang-Wang Lian, Yin Shi +4
We propose a new way of axial magnetic fields generation in a non-relativistic laser intensity regime by using a twisted light carrying orbital angular momentum (OAM) to stimulate…
First, Do No Harm: AI Supervisor Scaffolds Novice Growth in Counselor Education
Chen Xu, Zhenyu Lyu, Tian Lan +12
The most dangerous mistakes a novice counselor makes are not the obvious ones: they are utterances that sound caring while quietly violating professional ethics and leaving vulnera…
Programmable Neural Network Trojan for Pre-Trained Feature Extractor
Yu Ji, Zixin Liu, Xing Hu +2
Neural network (NN) trojaning attack is an emerging and important attack model that can broadly damage the system deployed with NN models. Existing studies have explored the outsou…
PIV-Based 3D Fluid Flow Reconstruction Using Light Field Camera
Zhong Li, Jinwei Ye, Yu Ji +2
Particle Imaging Velocimetry (PIV) estimates the flow of fluid by analyzing the motion of injected particles. The problem is challenging as the particles lie at different depths bu…
QGAN: Quantized Generative Adversarial Networks
Peiqi Wang, Dongsheng Wang, Yu Ji +5
The intensive computation and memory requirements of generative adversarial neural networks (GANs) hinder its real-world deployment on edge devices such as smartphones. Despite the…
Seeing A 3D World in A Grain of Sand
Yufan Zhang, Yu Ji, Yu Guo +1
We present a snapshot imaging technique for recovering 3D surrounding views of miniature scenes. Due to their intricacy, miniature scenes with objects sized in millimeters are diff…
Predicting Preschoolers' Externalizing Problems with Mother-Child Interaction Dynamics and Deep Learning
Xi Chen, Yu Ji, Cong Xia +1
Objective: Predicting children's future levels of externalizing problems helps to identify children at risk and guide targeted prevention. Existing studies have shown that mothers…
Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler
Yu Ji, YouHui Zhang, WenGuang Chen +1
Different from developing neural networks (NNs) for general-purpose processors, the development for NN chips usually faces with some hardware-specific restrictions, such as limited…
Text2Bundle: Towards Personalized Query-based Bundle Generation
Shixuan Zhu, Chuan Cui, JunTong Hu +3
Bundle generation aims to provide a bundle of items for the user, and has been widely studied and applied on online service platforms. Existing bundle generation methods mainly uti…
A Neural Rendering Framework for Free-Viewpoint Relighting
Zhang Chen, Anpei Chen, Guli Zhang +4
We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis and relighting using multi-view image inputs. Existing neural rendering (NR) does not explicitl…
Self-Attentive Sequential Recommendation with Cheap Causal Convolutions
Jiayi Chen, Wen Wu, Liye Shi +5
Sequential Recommendation is a prominent topic in current research, which uses user behavior sequence as an input to predict future behavior. By assessing the correlation strength…
Towards Security-Auditable LLM Agents: A Unified Graph Representation
Chaofan Li, Lyuye Zhang, Jintao Zhai +9
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. Howev…
Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction
Yufan Zhang, Yu Ji, Ayo Ajiboye +4
We present a diffusion-based method for relighting dynamic portrait videos with photorealism and temporal consistency. Our method is fueled by a hybrid training dataset that consis…
3D Face Reconstruction Using Color Photometric Stereo with Uncalibrated Near Point Lights
Zhang Chen, Yu Ji, Mingyuan Zhou +2
We present a new color photometric stereo (CPS) method that recovers high quality, detailed 3D face geometry in a single shot. Our system uses three uncalibrated near point lights…
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
Xing Hu, Ling Liang, Lei Deng +7
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject. Even those that dep…
Designs, Motion Mechanism, Motion Coordination, and Communication of Bionic Robot Fishes: A Survey
Zhiwei Yu, Kai Li, Yu Ji +1
In the last few years, there have been many new developments and significant accomplishments in the research of bionic robot fishes. However, in terms of swimming performance, exis…