papers

Publications (39)

physics.soc-ph2018

Quantifying memories: mapping urban perception

Shan He, Yuji Yoshimura, Jonas Helfer +3

What people choose to see, like, or remember is of profound interest to city planners and architects. Previous research suggests what people are more likely to store in their memor…

cs.LG2025

MC-GRU:a Multi-Channel GRU network for generalized nonlinear structural response prediction across structures

Shan He, Ruiyang Zhang

Accurate prediction of seismic responses and quantification of structural damage are critical in civil engineering. Traditional approaches such as finite element analysis could lac…

cs.LG2023

Perturbation-Based Two-Stage Multi-Domain Active Learning

Rui He, Zeyu Dai, Shan He +1

In multi-domain learning (MDL) scenarios, high labeling effort is required due to the complexity of collecting data from various domains. Active Learning (AL) presents an encouragi…

cs.CV2026

EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control

Yuzhe Weng, Haotian Wang, Yuanhong Yu +4

Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representati…

math.OC2021

Minimum-Time Earth-to-Mars Interplanetary Orbit Transfer Using Adaptive Gaussian Quadrature Collocation

Brittanny V. Holden, Shan He, Anil V. Rao

The problem of minimum-time, low-thrust, Earth-to-Mars interplanetary orbital trajectory optimization is considered. The minimum-time orbital transfer problem is modeled as a four-…

cs.CV2021

DFGC 2021: A DeepFake Game Competition

Bo Peng, Hongxing Fan, Wei Wang +20

This paper presents a summary of the DFGC 2021 competition. DeepFake technology is developing fast, and realistic face-swaps are increasingly deceiving and hard to detect. At the s…

q-bio.QM2016

MODA: MOdule Differential Analysis for weighted gene co-expression network

Dong Li, James B. Brown, Luisa Orsini +3

Gene co-expression network differential analysis is designed to help biologists understand gene expression patterns under different condition. By comparing different gene co-expres…

cs.RO2025

Improving Swimming Performance in Soft Robotic Fish with Distributed Muscles and Embedded Kinematic Sensing

Kevin Soto, Isabel Hess, Brandon Schrader +2

Bio-inspired underwater vehicles could yield improved efficiency, maneuverability, and environmental compatibility over conventional propeller-driven underwater vehicles. However,…

cs.CV2026

REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation

Haotian Wang, Yuzhe Weng, Jun Du +6

Diffusion models have significantly advanced the field of talking head generation (THG). However, slow inference speeds and prevalent non-autoregressive paradigms severely constrai…

cs.SI2019

Attributed Network Embedding for Incomplete Attributed Networks

Chengbin Hou, Shan He, Ke Tang

Attributed networks are ubiquitous since a network often comes with auxiliary attribute information e.g. a social network with user profiles. Attributed Network Embedding (ANE) has…

cs.AI2026

Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels

Yuzhe Weng, Haotian Wang, Xinyi Yu +4

Audio-driven human video generation has achieved remarkable success in monologue scenarios, largely driven by advancements in powerful video generation foundation models. Moving be…

q-bio.QM2022

MPVNN: Mutated Pathway Visible Neural Network Architecture for Interpretable Prediction of Cancer-specific Survival Risk

Gourab Ghosh Roy, Nicholas Geard, Karin Verspoor +1

Survival risk prediction using gene expression data is important in making treatment decisions in cancer. Standard neural network (NN) survival analysis models are black boxes with…

cs.SI2019

HEAT: Hyperbolic Embedding of Attributed Networks

David McDonald, Shan He

Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approa…

cs.SI2021

GloDyNE: Global Topology Preserving Dynamic Network Embedding

Chengbin Hou, Han Zhang, Shan He +1

Learning low-dimensional topological representation of a network in dynamic environments is attracting much attention due to the time-evolving nature of many real-world networks. T…

cs.SI2019

DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding

Chengbin Hou, Han Zhang, Ke Tang +1

Learning topological representation of a network in dynamic environments has recently attracted considerable attention due to the time-evolving nature of many real-world networks i…

cs.AI2026

Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization

Shan He, Runze Wang, Zhuoyun Du +4

Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat…

cs.IR2025

DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning

Qingyun Sun, Jiaqi Yuan, Shan He +5

Graph Retrieval-Augmented Generation has emerged as a powerful paradigm for grounding large language models with external structured knowledge. However, existing Graph RAG methods…

cs.LG2024

Dockformer: A transformer-based molecular docking paradigm for large-scale virtual screening

Zhangfan Yang, Junkai Ji, Shan He +5

Molecular docking is a crucial step in drug development, which enables the virtual screening of compound libraries to identify potential ligands that target proteins of interest. H…

cond-mat.stat-mech2009

Integrating fluctuations into distribution of resources in transportation networks

Shan He, Sheng Li, Hongru Ma

We propose a resource distribution strategy to reduce the average travel time in a transportation network given a fixed generation rate. Suppose that there are essential resources…

nucl-th2025

-decay half-lives and -cluster preformation factors of nuclei around line

Jing Li, Shan He, Yueqing Li +3

In this work, a microscopic effective nucleon-nucleon interaction based on the Dirac-Brueckner-Hartree-Fock matrix starting from a bare nucleon-nucleon interaction is used to e…

cs.CV2020

Lossless Attention in Convolutional Networks for Facial Expression Recognition in the Wild

Chuang Wang, Ruimin Hu, Min Hu +5

Unlike the constraint frontal face condition, faces in the wild have various unconstrained interference factors, such as complex illumination, changing perspective and various occl…

cs.SI2025

Influence Maximization Considering Influence, Cost and Time

Mingyang Feng, Qi Zhao, Shan He +1

Influence maximization has been studied for social network analysis, such as viral marketing (advertising), rumor prevention, and opinion leader identification. However, most studi…

cs.AI2026

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

Xinquan Chen, Zhenyun Yin, Shan He +38

As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment intera…

cond-mat.stat-mech2006

Effective delivering capacity in traffic dynamics based on scale-free network

Shan He, Sheng Li, Hongru Ma

We investigate the percentage of delivering capacities that are actually consumed in a typical traffic dynamics where the capacities are uniformly assigned over a scale-free networ…

cs.LG2023

Multi-Domain Learning From Insufficient Annotations

Rui He, Shengcai Liu, Jiahao Wu +2

Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-…

physics.soc-ph2008

Effect of edge removal on topological and functional robustness of complex networks

Shan He, Sheng Li, Hongru Ma

We study the robustness of complex networks subject to edge removal. Several network models and removing strategies are simulated. Rather than the existence of the giant component,…

cs.CV2024

EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion

Haotian Wang, Yuzhe Weng, Yueyan Li +10

Diffusion models have revolutionized the field of talking head generation, yet still face challenges in expressiveness, controllability, and stability in long-time generation. In t…

cs.CL2021

YACLC: A Chinese Learner Corpus with Multidimensional Annotation

Yingying Wang, Cunliang Kong, Liner Yang +8

Learner corpus collects language data produced by L2 learners, that is second or foreign-language learners. This resource is of great relevance for second language acquisition rese…

stat.AP2026

Understanding Long-Term Dynamics of Individual Metro Usage: A Hidden Semi-Markov State Framework with Survival Analysis

Bingxun Wang, Valeria Maria Urbano, Shan He +4

Understanding how individual metro usage evolves over multi-year horizons is essential for transit planning and passenger retention. However, existing approaches typically characte…

cs.SE2020

Ownership at Large -- Open Problems and Challenges in Ownership Management

John Ahlgren, Maria Eugenia Berezin, Kinga Bojarczuk +10

Software-intensive organizations rely on large numbers of software assets of different types, e.g., source-code files, tables in the data warehouse, and software configurations. Wh…

cs.LG2022

Multi-Domain Active Learning: Literature Review and Comparative Study

Rui He, Shengcai Liu, Shan He +1

Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each model is specialized to perform a task in a particular domain. Generally, a high labeling…

cs.ET2026

Embodying Intelligence into Mechanical Metamaterials via Reservoir Computing

Shan He, Steven Kiyabu, Philip R. Buskohl +1

This study harnesses the embodied intelligence of mechanical metamaterials to sense and process environmental vibrations with minimal digital computation. Using physical reservoir…

cs.CL2023

Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training

Dongfang Li, Baotian Hu, Qingcai Chen +1

Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI…

cs.SI2021

Robust Dynamic Network Embedding via Ensembles

Chengbin Hou, Guoji Fu, Peng Yang +3

Dynamic Network Embedding (DNE) has recently attracted considerable attention due to the advantage of network embedding in various fields and the dynamic nature of many real-world…

cs.RO2026

SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing

Aodi Wu, Haodong Han, Xubo Luo +3

Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D spatial situations, and execute multi-phase tasks over extended horizons…

cs.GR2025

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

Haotian Wang, Yuzhe Weng, Jun Du +7

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely lim…

cs.RO2025

A Real-time Spatio-Temporal Trajectory Planner for Autonomous Vehicles with Semantic Graph Optimization

Shan He, Yalong Ma, Tao Song +2

Planning a safe and feasible trajectory for autonomous vehicles in real-time by fully utilizing perceptual information in complex urban environments is challenging. In this paper,…

cs.AI2025

PoAct: Policy and Action Dual-Control Agent for Generalized Applications

Guozhi Yuan, Youfeng Liu, Jingli Yang +6

Based on their superior comprehension and reasoning capabilities, Large Language Model (LLM) driven agent frameworks have achieved significant success in numerous complex reasoning…

physics.ao-ph2025

Towards a Climate OSSE Framework for Satellite Mission Design

Ann M. Fridlind, Gregory S. Elsaesser, Marcus van Lier-Walqui +24

The rich history of observing system simulation experiments (OSSEs) does not yet include a well-established framework for using climate models. The need for a climate OSSE is trigg…