papers

Publications (195)

cs.LG2022

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas +19

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more…

cs.LG2024

Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning

Hanlin Yang, Jian Yao, Weiming Liu +13

Recovering a spectrum of diverse policies from a set of expert trajectories is an important research topic in imitation learning. After determining a latent style for a trajectory,…

math.QA2014

The Integral quantum loop algebra of

Jie Du, Qiang Fu

We will construct the Lusztig form for the quantum loop algebra of by proving the conjecture \cite[3.8.6]{DDF} and establish partially the Schur--Weyl duality at…

cs.LG2023

DIGMN: Dynamic Intent Guided Meta Network for Differentiated User Engagement Forecasting in Online Professional Social Platforms

Feifan Li, Lun Du, Qiang Fu +4

User engagement prediction plays a critical role for designing interaction strategies to grow user engagement and increase revenue in online social platforms. Through the in-depth…

stat.CO2024

Mean-field underdamped Langevin dynamics and its spacetime discretization

Qiang Fu, Ashia Wilson

We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures…

cs.AI2021

Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search

Sheng Chen, Menghui Zhu, Deheng Ye +3

Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome. State-of-the-art drafting methods fail to consider: 1) dr…

cs.AI2024

Playable Game Generation

Mingyu Yang, Junyou Li, Zhongbin Fang +5

In recent years, Artificial Intelligence Generated Content (AIGC) has advanced from text-to-image generation to text-to-video and multimodal video synthesis. However, generating pl…

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…

cs.AI2021

MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks

Menghui Zhu, Minghuan Liu, Jian Shen +7

In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem. In…

cs.NI2021

Multi-Agent Deep Reinforcement Learning for Request Dispatching in Distributed-Controller Software-Defined Networking

Victoria Huang, Gang Chen, Qiang Fu

Recently, distributed controller architectures have been quickly gaining popularity in Software-Defined Networking (SDN). However, the use of distributed controllers introduces a n…

cs.LG2023

Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning

Haoxuan Pan, Deheng Ye, Xiaoming Duan +4

We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is fo…

astro-ph.EP2026

Interstellar Object 3I/ATLAS Observed from Mars by China's Tianwen-1 Spacecraft

Xin Ren, Wei Yan, Ruining Zhao +20

China's Tianwen-1 Mars orbiter successfully imaged the third interstellar object, 3I/ATLAS, during its close encounter with Mars using the onboard HiRIC CMOS camera. This is China'…

cs.CV2023

Text-to-Image Generation for Abstract Concepts

Jiayi Liao, Xu Chen, Qiang Fu +5

Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the express…

cs.CL2022

Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models

Shengnan An, Yifei Li, Zeqi Lin +6

Recently the prompt-tuning paradigm has attracted significant attention. By only tuning continuous prompts with a frozen pre-trained language model (PLM), prompt-tuning takes a ste…

cs.SD2024

Robust Wake Word Spotting With Frame-Level Cross-Modal Attention Based Audio-Visual Conformer

Haoxu Wang, Ming Cheng, Qiang Fu +1

In recent years, neural network-based Wake Word Spotting achieves good performance on clean audio samples but struggles in noisy environments. Audio-Visual Wake Word Spotting (AVWW…

cs.NI2019

Optimizing Controller Placement for Software-Defined Networks

Victoria Huang, Gang Chen, Qiang Fu +1

Controller placement problem (CPP) is a key issue for Software-Defined Networking (SDN) with distributed controller architectures. This problem aims to determine a suitable number…

eess.IV2024

Neural Étendue Expander for Ultra-Wide-Angle High-Fidelity Holographic Display

Ethan Tseng, Grace Kuo, Seung-Hwan Baek +8

Holographic displays can generate light fields by dynamically modulating the wavefront of a coherent beam of light using a spatial light modulator, promising rich virtual and augme…

cs.SD2021

Weighted Recursive Least Square Filter and Neural Network based Residual Echo Suppression for the AEC-Challenge

Ziteng Wang, Yueyue Na, Zhang Liu +2

This paper presents a real-time Acoustic Echo Cancellation (AEC) algorithm submitted to the AEC-Challenge. The algorithm consists of three modules: Generalized Cross-Correlation wi…

math.QA2013

Quantum affine via Hecke algebras

Jie Du, Qiang Fu

We use the Hecke algebras of affine symmetric groups and their associated Schur algebras to construct a new algebra through a basis, and a set of generators and explicit multiplica…

cond-mat.mtrl-sci2022

One-step exfoliation method for plasmonic activation of large-area 2D crystals

Qiang Fu, Jia-Qi Dai, Xin-Yu Huang +16

Advanced exfoliation techniques are crucial for exploring the intrinsic properties and applications of 2D materials. Though the recently discovered Au-enhanced exfoliation techniqu…

cs.LG2026

Test-Time Learning of Causal Structure from Interventional Data

Wei Chen, Rui Ding, Bojun Huang +5

Supervised causal learning has shown promise in causal discovery, yet it often struggles with generalization across diverse interventional settings, particularly when intervention…

cs.LG2025

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

Yuxiang Zhang, Zhengxu Yu, Weihang Pan +5

Emerging reasoning LLMs such as OpenAI-o1 and DeepSeek-R1 have achieved strong performance on complex reasoning tasks by generating long chain-of-thought (CoT) traces. However, the…

cs.CV2013

Scan-based Compressed Terahertz Imaging and Real-Time Reconstruction via the Complex-valued Fast Block Sparse Bayesian Learning Algorithm

Benyuan Liu, Hongqi Fan, Zaiqi Lu +1

Compressed Sensing based Terahertz imaging (CS-THz) is a computational imaging technique. It uses only one THz receiver to accumulate the random modulated image measurements where…

cs.LG2022

DGI: Easy and Efficient Inference for GNNs

Peiqi Yin, Xiao Yan, Jinjing Zhou +5

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopte…

cs.LG2023

Future-conditioned Unsupervised Pretraining for Decision Transformer

Zhihui Xie, Zichuan Lin, Deheng Ye +3

Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promi…

eess.IV2022

A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging

Jingang Zhang, Runmu Su, Wenqi Ren +3

Hyperspectral imaging enables versatile applications due to its competence in capturing abundant spatial and spectral information, which are crucial for identifying substances. How…

cs.LG2021

Boosting Offline Reinforcement Learning with Residual Generative Modeling

Hua Wei, Deheng Ye, Zhao Liu +5

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration. Current offline RL research includes: 1) gen…

math.QA2012

Integral affine Schur-Weyl reciprocity

Qiang Fu

Let be the double Ringel--Hall algebra of the cyclic quiver and let

cs.CV2023

Aberration-Aware Depth-from-Focus

Xinge Yang, Qiang Fu, Mohammed Elhoseiny +1

Computer vision methods for depth estimation usually use simple camera models with idealized optics. For modern machine learning approaches, this creates an issue when attempting t…

math.OC2023

Accelerated Stochastic Optimization Methods under Quasar-convexity

Qiang Fu, Dongchu Xu, Ashia Wilson

Non-convex optimization plays a key role in a growing number of machine learning applications. This motivates the identification of specialized structure that enables sharper theor…

cs.SD2015

Noise Robust IOA/CAS Speech Separation and Recognition System For The Third 'CHIME' Challenge

Xiaofei Wang, Chao Wu, Pengyuan Zhang +5

This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition. In…

cs.SD2021

Joint Online Multichannel Acoustic Echo Cancellation, Speech Dereverberation and Source Separation

Yueyue Na, Ziteng Wang, Zhang Liu +2

This paper presents a joint source separation algorithm that simultaneously reduces acoustic echo, reverberation and interfering sources. Target speeches are separated from the mix…

econ.TH2024

Orchestrating Organizational Politics: Baron and Ferejohn Meet Tullock

Qiang Fu, Zenan Wu, Yuxuan Zhu

This paper examines the optimal organizational rules that govern the process of dividing a fixed surplus. The process is modeled as a sequential multilateral bargaining game with c…

cs.CL2023

How Do In-Context Examples Affect Compositional Generalization?

Shengnan An, Zeqi Lin, Qiang Fu +4

Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence. The AI community mainly studies this…

math.QA2012

Small Representations for Affine q-Schur Algebras

Jie Du, Qiang Fu

When the parameter is not a root of unity, simple modules of affine -Schur algebras have been classified in terms of Frenkel--Mukhin's dominant Drinfeld polyno…

physics.ins-det2022

Transition edge sensor based detector: from X-ray to -ray

Shuo Zhang, Jing-Kai Xia, Tao Sun +15

The Transition Edge Sensor is extremely sensitive to the change of temperature, combined with the high-Z metal of a certain thickness, it can realize the high energy resolution mea…

cs.LG2023

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

Tiantian Zhang, Zichuan Lin, Yuxing Wang +7

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while m…

math.RT2011

On the structure of

Qiang Fu, Qunguang Yang

Let be the infinitesimal quantum over , where is a field containing an th primitive root of 1 with {\it odd}. We will determine the…

eess.SY2026

Dynamic Analysis of Centralized Energy Storage Systems -- A Comparison between Grid-following and Grid-forming Controls

Qiang Fu, Siqi Bu, Yang Wang +1

This study investigates the small-signal stability of centralized energy storage systems (CESSs) using grid-following (GFL) and grid-forming (GFM) controls, particularly focusing o…

cs.IR2023

On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering

Jiayan Guo, Lun Du, Xu Chen +5

Collaborative filtering (CF) is an important research direction in recommender systems that aims to make recommendations given the information on user-item interactions. Graph CF h…

astro-ph.IM2014

Experimental study on Modified Linear Quadratic Gaussian Control for Adaptive Optics

Qiang Fu, Jörg-Uwe Pott, Peter Dethard +3

To achieve high resolution imaging the standard control algorithm used for classical adaptive optics (AO) is the simple but efficient proportional-integral (PI) controller. The goa…

cs.SD2021

Controllable Multichannel Speech Dereverberation based on Deep Neural Networks

Ziteng Wang, Yueyue Na, Biao Tian +1

Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early ref…

cs.SD2025

DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment

Zongcai Du, Guilin Deng, Xiaofeng Guo +8

Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-s…

cs.CV2022

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

Boxuan Zhao, Jun Zhang, Deheng Ye +4

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic rele…

cs.AI2024

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Yun Qu, Boyuan Wang, Jianzhun Shao +15

The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected o…

stat.ML2026

Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space

Kyurae Kim, Qiang Fu, Yi-An Ma +2

For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example…

math.QA2026

Quantum current algebra : canonical bases, rigidity, and relation with Yangians

Qiang Fu

We introduce a quantum deformation of the universal enveloping algebra of the current algebra , realized as a parabolic subalge…

cs.LG2025

Deep (Predictive) Discounted Counterfactual Regret Minimization

Hang Xu, Kai Li, Haobo Fu +3

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR's applicability in large games, researchers u…

cs.CL2024

More Agents Is All You Need

Junyou Li, Qin Zhang, Yangbin Yu +2

We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method, termed as A…

math.QA2011

Quantum , infinite -Schur algebras and their representations

Jie Du, Qiang Fu

In this paper, we investigate the structure and representations of the quantum group . We will present a realization for…

cs.SE2017

Code review and cooperative pair programming best practice

Qiang Fu, Francis Grady, Bjoern Flemming Broberg +4

We need ways to improve the code quality. Programmers have different level of tenure and experience. Standard and programming languages change and we are forced to re-use legacy co…

eess.IV2025

Latent Space Imaging

Matheus Souza, Yidan Zheng, Kaizhang Kang +3

Digital imaging systems have traditionally relied on brute-force measurement and processing of pixels arranged on regular grids. In contrast, the human visual system performs signi…

cond-mat.mes-hall2020

Interlayer Decoupling in 30° Twisted Bilayer Graphene Quasicrystal

Bing Deng, Binbin Wang, Ning Li +8

Stacking order has strong influence on the coupling between the two layers of twisted bilayer graphene (BLG), which in turn determines its physical properties. Here, we report the…

cs.IR2019

Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System

Muhammad Ammad-ud-din, Elena Ivannikova, Suleiman A. Khan +4

The increasing interest in user privacy is leading to new privacy preserving machine learning paradigms. In the Federated Learning paradigm, a master machine learning model is dist…

physics.optics2011

Direct characterization of planar waveguide modes by Fourier plane fluorescence leakage radiation microscopy

Douguo Zhang, Qiang Fu, Xiangxian Wang +2

In this letter, the leakage radiation microscopy (LRM) is extended into characterization of planar waveguide modes (WMs) rather than surface plasmon polaritons (SPPs) taking advant…

cs.AI2024

Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination

Liangzhou Wang, Kaiwen Zhu, Fengming Zhu +6

Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However…

cs.CV2025

HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes

Changfeng Feng, Zhenyuan Chen, Xiang Li +5

Object detection from aerial platforms under adverse atmospheric conditions, particularly haze, is paramount for robust drone autonomy. Yet, this domain remains largely underexplor…

cs.AI2024

Enhance Reasoning for Large Language Models in the Game Werewolf

Shuang Wu, Liwen Zhu, Tao Yang +4

This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents.…

cs.CV2022

Sparse Optical Flow-Based Line Feature Tracking

Qiang Fu, Hongshan Yu, Islam Ali +1

In this paper we propose a novel sparse optical flow (SOF)-based line feature tracking method for the camera pose estimation problem. This method is inspired by the point-based SOF…

cs.LG2021

Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective

Lun Du, Xu Chen, Fei Gao +4

Network Embedding aims to learn a function mapping the nodes to Euclidean space contribute to multiple learning analysis tasks on networks. However, the noisy information behind th…

cs.SD2021

NN3A: Neural Network supported Acoustic Echo Cancellation, Noise Suppression and Automatic Gain Control for Real-Time Communications

Ziteng Wang, Yueyue Na, Biao Tian +1

Acoustic echo cancellation (AEC), noise suppression (NS) and automatic gain control (AGC) are three often required modules for real-time communications (RTC). This paper proposes a…

cond-mat.mtrl-sci2013

Tailoring exciton dynamics by elastic strain-gradient in semiconductors

Xuewen Fu, Cong Su, Qiang Fu +7

As device miniaturization approaches the atomic limit, it becomes highly desirable to exploit novel paradigms for tailoring electronic structures and carrier dynamics in materials.…

hep-ph2023

Deeply Virtual Compton Scattering at Future Electron-Ion Colliders

Gang Xie, Wei Kou, Qiang Fu +2

The study of hadronic structure has been carried out for many years. Generalized parton distribution functions (GPDs) give broad information on the internal structure of hadrons. C…

math.RT2011

Representations of little -Schur algebras

Jie Du, Qiang Fu, Jian-pan Wang

In \cite{DFW} and \cite{Fu07}, little -Schur algebras were introduced as homomorphic images of the infinitesimal quantum groups. In this paper, we will investigate representatio…

cond-mat.soft2009

Novel polymer nanocomposite composed of organic nanoparticles via self-assembly

Dequan Xiao, Kunhua Lin, Qiang Fu +1

We report a novel class of polymer nanocomposite composed of organic nanoparticles dispersed in polymer matrix, with the particle sizes of 30-120 nm in radius. The organic nanopart…

cs.LG2022

Neuron with Steady Response Leads to Better Generalization

Qiang Fu, Lun Du, Haitao Mao +4

Regularization can mitigate the generalization gap between training and inference by introducing inductive bias. Existing works have already proposed various inductive biases from…

physics.ins-det2015

IsoDAR Neutrino Experiment Simulation with Proton and Deuteron Beams

Fengyi Zhao, Yao Li, Chengdong Han +2

In this paper we consider high-intensity source of electron antineutrinos from the production and subsequent decay of 8Li. It opens a wide range of possible searches for beyond sta…

cs.CV2025

Limitations of Data-Driven Spectral Reconstruction -- An Optics-Aware Analysis

Qiang Fu, Matheus Souza, Eunsue Choi +3

Hyperspectral imaging empowers machine vision systems with the distinct capability of identifying materials through recording their spectral signatures. Recent efforts in data-driv…

cs.NE2024

Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution

Ke Xue, Yutong Wang, Cong Guan +5

Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some stu…

cs.SD2022

ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting

Dianwen Ng, Yunqi Chen, Biao Tian +2

Building efficient architecture in neural speech processing is paramount to success in keyword spotting deployment. However, it is very challenging for lightweight models to achiev…

cs.CL2024

Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models

Yuyan Chen, Qiang Fu, Yichen Yuan +6

Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawb…

cs.CV2017

Hyperspectral Light Field Stereo Matching

Kang Zhu, Yujia Xue, Qiang Fu +3

In this paper, we describe how scene depth can be extracted using a hyperspectral light field capture (H-LF) system. Our H-LF system consists of a 5 x 6 array of cameras, with each…

math.QA2014

Positivity properties for canonical bases of modified quantum affine

Qiang Fu, Toshiaki Shoji

The positivity property for canonical bases asserts that the structure constants of the multiplication for the canonical basis are in . Let be th…

cs.SD2022

Multi-Task Deep Residual Echo Suppression with Echo-aware Loss

Shimin Zhang, Ziteng Wang, Jiayao Sun +4

This paper introduces the NWPU Team's entry to the ICASSP 2022 AEC Challenge. We take a hybrid approach that cascades a linear AEC with a neural post-filter. The former is used to…

cond-mat.mtrl-sci2024

Effects of Structural Variations to X-ray Absorption Spectra of g-CN: Insights from DFT and TDDFT Simulations

Jun-Rong Zhang, Sheng-Yu Wang, Minrui Wei +2

X-ray absorption spectroscopy (XAS) is widely employed for structure characterization of graphitic carbon nitride (g-CN) and its composites. Nevertheless, even for pure g-C…

cs.LG2022

Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach

Wendong Bi, Lun Du, Qiang Fu +3

Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data. A lot of GNNs perform well on homophily graphs while having unsatisfactory performance on…

cs.CV2026

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

Tianyuan Zhang, Lu Wang, Xinwei Zhang +7

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial…

cs.SI2023

Homophily-oriented Heterogeneous Graph Rewiring

Jiayan Guo, Lun Du, Wendong Bi +6

With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG) have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown great potenti…

cs.LG2026

Test Time Training for Supervised Causal Learning

Zizhen Deng, Jiaru Zhang, Rui Ding +5

Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution gene…

cs.MA2025

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

Jiarong Liu, Yifan Zhong, Siyi Hu +4

Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing state-of-the-art methods face challenges related to samp…

cond-mat.mtrl-sci2018

Polaron-induced band renormalization due to linear and quadratic electron-phonon coupling

Pablo García Risueño, Dmitrii Nabok, Qiang Fu +1

We present a novel approach to electron-lattice interaction beyond the linear-coupling regime. Based on the solution of a Holstein-Peierls-type model, we derive explicit analytical…

cs.LG2025

Agents Play Thousands of 3D Video Games

Zhongwen Xu, Xianliang Wang, Siyi Li +4

We present PORTAL, a novel framework for developing artificial intelligence agents capable of playing thousands of 3D video games through language-guided policy generation. By tran…

cs.RO2022

PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features

Qiang Fu, Jialong Wang, Hongshan Yu +4

Leveraging line features to improve localization accuracy of point-based visual-inertial SLAM (VINS) is gaining interest as they provide additional constraints on scene structure.…

cs.LG2021

Learning Diverse Policies in MOBA Games via Macro-Goals

Yiming Gao, Bei Shi, Xueying Du +10

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings. Ev…

cs.AI2020

Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

Deheng Ye, Zhao Liu, Mingfei Sun +15

We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and…

cs.LG2025

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Jinmin He, Kai Li, Yifan Zang +4

Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any onlin…

cs.RO2021

Vision-Based Target Localization for a Flapping-Wing Aerial Vehicle

Xinghao Dong, Qiang Fu, Chunhua Zhang +1

The flapping-wing aerial vehicle (FWAV) is a new type of flying robot that mimics the flight mode of birds and insects. However, FWAVs have their special characteristics of less lo…

cs.LG2023

Robust Mid-Pass Filtering Graph Convolutional Networks

Jincheng Huang, Lun Du, Xu Chen +3

Graph convolutional networks (GCNs) are currently the most promising paradigm for dealing with graph-structure data, while recent studies have also shown that GCNs are vulnerable t…

math.QA2012

BLM realization for the integral form of quantum

Qiang Fu

Let be the quantum enveloping algebra of over , where is an indeterminate. We will use -Schur algebras to realize the integra…

cs.SI2022

HTGN-BTW: Heterogeneous Temporal Graph Network with Bi-Time-Window Training Strategy for Temporal Link Prediction

Chongjian Yue, Lun Du, Qiang Fu +4

With the development of temporal networks such as E-commerce networks and social networks, the issue of temporal link prediction has attracted increasing attention in recent years.…

math.QA2013

BLM realization for Frobenius--Lusztig Kernels of type A

Qiang Fu

The infinitesimal quantum was realized in \cite[§6]{BLM}. We will realize Frobenius--Lusztig Kernels of type in this paper.

cs.AI2020

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

Deheng Ye, Guibin Chen, Peilin Zhao +15

We present JueWu-SL, the first supervised-learning-based artificial intelligence (AI) program that achieves human-level performance in playing multiplayer online battle arena (MOBA…

cs.SD2022

Personalized Acoustic Echo Cancellation for Full-duplex Communications

Shimin Zhang, Ziteng Wang, Yukai Ju +4

Deep neural networks (DNNs) have shown promising results for acoustic echo cancellation (AEC). But the DNN-based AEC models let through all near-end speakers including the interfer…

cs.HC2024

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

Yiming Gao, Feiyu Liu, Liang Wang +12

Existing game AI research mainly focuses on enhancing agents' abilities to win games, but this does not inherently make humans have a better experience when collaborating with thes…

cs.CL2026

Kimi K3: Open Frontier Intelligence

Kimi Team, Tongtong Bai, Yifan Bai +398

We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…

cond-mat.mtrl-sci2018

Hybrid Organic-Inorganic Perovskites as Promising Substrates for Pt Single-Atom Catalysts

Qiang Fu, Claudia Draxl

Single-atom catalysts (SACs) combine the best of two worlds by bridging heterogeneous and homogeneous catalysis. The superior catalytic properties of SACs, however, can hardly be e…

physics.optics2026

Tunable, high pulse energy and narrow linewidth gas-filled fiber laser across near- and mid-infrared

Yazhou Wang, Marcello Meneghetti, Manoj K. Dasa +9

Wavelength widely tunable infrared fiber lasers that simultaneously deliver high pulse energies with narrow linewidths are critical for applications ranging from spectroscopy to no…

physics.ao-ph2023

Characteristics of Gravity Waves in Opposing Phases of the QBO: A Reanalysis Perspective with ERA5

Hamid A. Pahlavan, John M. Wallace, Qiang Fu +1

ERA5 data for the period of 1979-2019 are used as a basis for investigating the properties of gravity waves as they disperse and propagate upward through the stratosphere during op…

cs.LG2022

Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning

Hua Wei, Jingxiao Chen, Xiyang Ji +11

This paper introduces Honor of Kings Arena, a reinforcement learning (RL) environment based on Honor of Kings, one of the world's most popular games at present. Compared to other e…

cs.CV2025

PRJ: Perception-Retrieval-Judgement for Generated Images

Qiang Fu, Zonglei Jing, Zonghao Ying +1

The rapid progress of generative AI has enabled remarkable creative capabilities, yet it also raises urgent concerns regarding the safety of AI-generated visual content in real-wor…