papers

Publications (44)

cs.CV2026

Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation

Mingyang Huang, Peng Zhang, Li Hu +5

The paper introduces Wan-Dancer, a hierarchical framework that generates minute‑scale, high‑definition dance videos synchronized to music by separating global keyframe planning fro…

#music-to-dance generation#hierarchical modeling#long-duration video synthesis#diffusion models
cs.CV2026

MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

Zhongyi Zhang, Guangyuan Wang, Li Hu +6

The paper presents MultiAnimate, a framework that can animate several characters together in a shared scene while keeping each character's appearance and spatial relationships cons…

#multi-character animation#identity preservation#pose encoding#interaction modeling
cs.CV2021

Learning Position and Target Consistency for Memory-based Video Object Segmentation

Li Hu, Peng Zhang, Bang Zhang +3

This paper studies the problem of semi-supervised video object segmentation(VOS). Multiple works have shown that memory-based approaches can be effective for video object segmentat…

cs.CV2019

Double Anchor R-CNN for Human Detection in a Crowd

Kevin Zhang, Feng Xiong, Peize Sun +3

Detecting human in a crowd is a challenging problem due to the uncertainties of occlusion patterns. In this paper, we propose to handle the crowd occlusion problem in human detecti…

cond-mat.mes-hall2016

Quantitatively analyzing intrinsic plasmonic chirality by tracking the interplay of electric and magnetic dipole modes

Li Hu, Yingzhou Huang, Yurui Fang

Plasmonic chirality exhibits great potential for novel nanooptical devices due to the generation of a strong chiroptical response. Previous reports on plasmonic chirality explanati…

cs.LG2026

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression

Ruijie Zhang, Haozhe Liang, Da Chang +4

Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this cost by keeping only part of the…

cs.CV2025

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

Gang Cheng, Xin Gao, Li Hu +23

We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by preci…

cs.SE2025

BinMetric: A Comprehensive Binary Analysis Benchmark for Large Language Models

Xiuwei Shang, Guoqiang Chen, Shaoyin Cheng +5

Binary analysis remains pivotal in software security, offering insights into compiled programs without source code access. As large language models (LLMs) continue to excel in dive…

cs.CV2025

Wan-S2V: Audio-Driven Cinematic Video Generation

Xin Gao, Li Hu, Siqi Hu +20

Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they o…

cs.SE2024

How Far Have We Gone in Binary Code Understanding Using Large Language Models

Xiuwei Shang, Shaoyin Cheng, Guoqiang Chen +6

Binary code analysis plays a pivotal role in various software security applications, such as software maintenance, malware detection, software vulnerability discovery, patch analys…

cs.LG2025

Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy

Yaxin Xiao, Qingqing Ye, Li Hu +5

Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to…

cs.CV2026

Wan-Animate-2: Pushing the Application Boundaries of Character Animation

Guangyuan Wang, Li Hu, Dechao Meng +11

Character image animation remains a foundational yet challenging task in computer vision. Existing approaches can be broadly categorized into three paradigms: methods based on expl…

physics.optics2015

Fano resonance assisting plasmonic circular dichroism from nanorice heterodimers for extrinsic chirality

Li Hu, Yingzhou Huang, Liang Fang +3

In this work, the circular dichroisms (CD) of nanorice heterodimers consisting of two parallel arranged nanorices with the same size but different materials are investigated theore…

cs.CV2025

Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance

Li Hu, Guangyuan Wang, Zhen Shen +6

Recent character image animation methods based on diffusion models, such as Animate Anyone, have made significant progress in generating consistent and generalizable character anim…

cs.SE2025

CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System

Li Hu, Guoqiang Chen, Xiuwei Shang +6

With open-source projects growing in size and complexity, manual compilation becomes tedious and error-prone, highlighting the need for automation to improve efficiency and accurac…

gr-qc2025

Distinctive GWBs from eccentric inspiraling SMBH binaries with a DM spike

Li Hu, Rong-Gen Cai, Shao-Jiang Wang

Recent detections of a low-frequency gravitational wave background (GWB) from various pulsar-timing-array (PTA) observations have renewed the interest in the inspiraling supermassi…

cs.CL2025

dots.llm1 Technical Report

Bi Huo, Bin Tu, Cheng Qin +24

Mixture of Experts (MoE) models have emerged as a promising paradigm for scaling language models efficiently by activating only a subset of parameters for each input token. In this…

cs.IT2019

Machine Learning-based Signal Detection for PMH Signals in Load-modulated MIMO System

Jinle Zhu, Qiang Li, Li Hu +2

Phase Modulation on the Hypersphere (PMH) is a power efficient modulation scheme for the \textit{load-modulated} multiple-input multiple-output (MIMO) transmitters with central pow…

cs.CV2022

Recurrent Dynamic Embedding for Video Object Segmentation

Mingxing Li, Li Hu, Zhiwei Xiong +3

Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the…

cs.SE2026

Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation

Li Hu, Xiuwei Shang, Jieke Shi +6

Deobfuscating binary code remains a fundamental challenge in reverse engineering, as obfuscation is widely used to hinder analysis and conceal program logic. Although large languag…

math.NA2022

Reduce the rank calculation of a high-dimensional sparse matrix based on network controllability theory

Chen Zhao, Yuqing Liu, Li Hu +1

Numerical computing of the rank of a matrix is a fundamental problem in scientific computation. The datasets generated by the internet often correspond to the analysis of high-dime…

physics.optics2022

Plasmonic and photonic enhancement of chiral near fields

Li Hu, Zhiguang Sun, Yingdong Nie +2

A chiral near field with a highly contorted electromagnetic field builds a bridge to match the chiral molecules and light wavelengths with large size differences. It significantly…

gr-qc2026

Third law of repetitive electric Penrose processes

Li Hu, Rong-Gen Cai, Shao-Jiang Wang

Recently, Ruffini et al. [Phys. Rev. Lett. 134 (2025) 8, 081403] pointed out that the repetitive Penrose process cannot drain the entire extractable energy of a Kerr black hole. In…

cs.SE2024

Binary Code Similarity Detection via Graph Contrastive Learning on Intermediate Representations

Xiuwei Shang, Li Hu, Shaoyin Cheng +4

Binary Code Similarity Detection (BCSD) plays a crucial role in numerous fields, including vulnerability detection, malware analysis, and code reuse identification. As IoT devices…

cs.SE2025

An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding

Xiuwei Shang, Zhenkan Fu, Shaoyin Cheng +5

Binary code analysis plays a pivotal role in the field of software security and is widely used in tasks such as software maintenance, malware detection, software vulnerability disc…

physics.optics2020

Long- and Short-Ranged Chiral Interactions in DNA Assembled Plasmonic Chains

Kevin Martens, Felix Binkowski, Linh Nguyen +4

Molecular chirality plays a crucial role in innumerable biological processes. The chirality of a molecule can typically be identified by its characteristic optical response, the ci…

cs.SE2026

Cross-modal Retrieval Models for Stripped Binary Analysis

Guoqiang Chen, Lingyun Ying, Ziyang Song +7

Retrieving binary code via natural language queries is a pivotal capability for downstream tasks in the software security domain, such as vulnerability detection and malware analys…

cond-mat.mes-hall2015

Quantitatively analyzing the mechanism of giant circular dichroism in extrinsic plasmonic chiral nanostructures by the interplay of electric and magnetic dipoles

Li Hu, Xiaorui Tian, Yingzhou Huang +2

The plasmonic chirality has drawn a lot of attention because of the tunable circular dichroism (CD) and the enhancement for the signal of chiral molecules. Different mechanisms hav…

physics.optics2009

Spherical cloaking using nonlinear transformations for improved segmentation into concentric isotropic coatings

Cheng-Wei Qiu, Li Hu, Baile Zhang +3

Two novel classes of spherical invisibility cloaks based on nonlinear transformation have been studied. The cloaking characteristics are presented by segmenting the nonlinear trans…

cs.SE2026

Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering

Xiuwei Shang, Li Hu, Xiao Jiang +7

Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing the cognitive burden of revers…

cs.CV2026

WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction

Li Hu, Guangyuan Wang, Peng Zhang +1

WanToFight is a generative game engine that uses a video diffusion transformer to produce real-time, two-player fighting game visuals from keyboard inputs, handling multi-player co…

#generative models#real-time inference#multi-player gaming#video diffusion
gr-qc2026

Thermodynamics of Kerr-Bertotti-Robinson black hole

Li Hu, Rong-Gen Cai, Shao-Jiang Wang

We investigate the thermodynamic properties of the Kerr-Bertotti-Robinson black hole, an exact Petrov type D solution of Einstein-Maxwell theory describing a rotating black hole im…

cs.CV2024

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Li Hu, Xin Gao, Peng Zhang +3

Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation resea…

cs.AI2026

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

Kanghua Mo, Li Hu, Yucheng Long +1

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradi…

gr-qc2025

Dynamical friction can flip the hierarchical three-body system

Li Hu, Rong-Gen Cai, Shao-Jiang Wang

In recent years, the long-term effects of non-linear perturbations were found to be important for the evolution of the hierarchical triple system, which, for the central third body…

gr-qc2026

Prospect on constraining environment-dependent dilaton model from gravitational redshift measurements

Li Hu, Rong-Gen Cai, Song He +4

Scalar-tensor gravity represents a natural extension of general relativity. This paper investigates a conformal scalar-tensor gravity, the environmentally dependent dilaton model,…

physics.soc-ph2021

Control core of undirected complex networks

Zhengzhong Yuan, Jingwen Li, Chen Zhao +2

With the development of complex networks, many researchers have paid greater attention to studying the control of complex networks over the last decade. Although some theoretical b…

cs.CR2026

Beyond the Edge of Function: Unraveling the Patterns of Type Recovery in Binary Code

Gangyang Li, Xiuwei Shang, Shaoyin Cheng +5

Type recovery is a crucial step in binary code analysis, holding significant importance for reverse engineering and various security applications. Existing works typically simply t…

cs.OH2023

DanceMeld: Unraveling Dance Phrases with Hierarchical Latent Codes for Music-to-Dance Synthesis

Xin Gao, Li Hu, Peng Zhang +2

In the realm of 3D digital human applications, music-to-dance presents a challenging task. Given the one-to-many relationship between music and dance, previous methods have been li…

cond-mat.mes-hall2015

Heterodimer nanostructures induced energy focusing on metal film

Ting Liu, Jingjing Hao, Yingzhou Huang +3

As an interesting surface plasmon phenomenon discovered several years ago, electromagnetic field redistribution in nanoparticle dimer on film system provides a novel thought to enh…

cs.NI2014

Utility Optimal Scheduling in Degree-Limited Satellite Networks

Li Hu, Liu Yuan`an, Yuan Dongming +2

In this paper, we consider the problem of flow control together with power allocation to antennas on satellite with arbitrary link states, so as to maximize the utility function wh…

gr-qc2026

Black hole-de Sitter space as the fastest transmitter and receiver

Rong-Gen Cai, Li Hu, Shao-Jiang Wang

It is well-known that the unitary nature of black hole evaporation enforces its entropy evolution to follow the Page curve. In this Letter, we find that the quantum speed limit on…

econ.GN2019

The Politics of Attention

Li Hu, Anqi Li

We develop an equilibrium theory of attention and politics. In a spatial model of electoral competition where candidates have varying policy preferences, we examine what kinds of p…

cs.CV2026

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models

Tianxing Xu, Zixuan Wang, Guangyuan Wang +5

World models based on video generation demonstrate remarkable potential for simulating interactive environments yet suffer from persistent difficulties in two key areas: maintainin…