Publications (72)
MORE-R1: Guiding LVLM for Multimodal Object-Entity Relation Extraction via Stepwise Reasoning with Reinforcement Learning
Xiang Yuan, Xu Chu, Xinrong Chen +6
Multimodal Object-Entity Relation Extraction (MORE) is a challenging task in information extraction research. It aims to identify relations between visual objects and textual entit…
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
V Team, Wenyi Hong, Wenmeng Yu +90
We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this…
Application Of Support Vector Machines To Global Prediction Of Nuclear Properties
John W. Clark, Haochen Li
Advances in statistical learning theory present the opportunity to develop statistical models of quantum many-body systems exhibiting remarkable predictive power. The potential of…
Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector
Junhao Wei, Yanxiao Li, Bidong Chen +9
We present a unified experiment, analysis, and benchmark study of multivariate time-series (MTS) anomaly detection. Ten family-representative detectors -- spanning statistical, rec…
CICDWOA: A Collective Cognitive Sharing Whale Optimization Algorithm with Cauchy Inverse Cumulative Distribution for 2D/3D Path Planning and Engineering Design Problems
Junhao Wei, Yanxiao Li, Seyedali Mirjalili +12
The Whale Optimization Algorithm (WOA) has shown strong optimization ability but still suffers from premature convergence and weak search diversity. To address these issues, this p…
Modeling Nuclear Properties with Support Vector Machines
Haochen Li, J. W. Clark, E. Mavrommatis +2
We have made initial studies of the potential of support vector machines (SVM) for providing statistical models of nuclear systematics with demonstrable predictive power. Using SVM…
Learning Domain-Aware Detection Head with Prompt Tuning
Haochen Li, Rui Zhang, Hantao Yao +5
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reduci…
KIO-planner: Attention-Guided Single-Stage Motion Planning with Dual Mapping for UAV Navigation
Dexing Yao, Haochen Li, Junhao Wei +11
Autonomous UAV flight in confined, wall-dense environments requires low-latency and reliable motion planning under strict safety constraints. Traditional optimization-based planner…
Joint Event Extraction via Structural Semantic Matching
Haochen Li, Tianhao Gao, Jingkun Wang +1
Event Extraction (EE) is one of the essential tasks in information extraction, which aims to detect event mentions from text and find the corresponding argument roles. The EE task…
MIND: Microstructure INverse Design with Generative Hybrid Neural Representation
Tianyang Xue, Haochen Li, Longdu Liu +7
The inverse design of microstructures plays a pivotal role in optimizing metamaterials with specific, targeted physical properties. While traditional forward design methods are con…
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
Haochen Li, Rui Zhang, Hantao Yao +7
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can…
The Nonradial Oscillation Node Precession of Neutron Stars
Haochen Li
The standing wave nodes of nonradial oscillations on a neutron star crust will drift with a definite angle velocity around rotational pole due to the rotation of neutron stars. Thi…
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Holy Lovenia, Rahmad Mahendra, Salsabil Maulana Akbar +58
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing…
Near-Field Beamforming for STAR-RIS Networks
Haochen Li, Yuanwei Liu, Xidong Mu +3
Recently, simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) have received significant research interest. The employment of large STAR-RIS a…
An Empirical Analysis on Financial Markets: Insights from the Application of Statistical Physics
Haochen Li, Yi Cao, Maria Polukarov +1
In this study, we introduce a physical model inspired by statistical physics for predicting price volatility and expected returns by leveraging Level 3 order book data. By drawing…
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
Qirui Zhou, Shaohui Peng, Weiqiang Xiong +11
The attention operator remains a critical performance bottleneck in large language models (LLMs), particularly for long-context scenarios. While FlashAttention is the most widely u…
Merging of single-particle levels and non-Fermi-liquid behavior of finite Fermi systems
V. A. Khodel, J. W. Clark, Haochen Li +1
We examine the problem of finite Fermi systems having a degenerate single-particle spectrum and show that the Landau approach, applied to such a system, admits the possibility of m…
Towards Goal-oriented Prompt Engineering for Large Language Models: A Survey
Haochen Li, Jonathan Leung, Zhiqi Shen
Large Language Models (LLMs) have shown prominent performance in various downstream tasks and prompt engineering plays a pivotal role in optimizing LLMs' performance. This paper, n…
Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling
Junhao Wei, Yanxiao Li, Yifu Zhao +8
Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Scheduling Problem (JSSP) heuri…
Beamforming Design for Pinching Antenna Systems Enabled Cognitive Radio Systems
Haochen Li, Ruikang Zhong, Zhaoming Hu +3
A pinching antenna system (PASS) assisted cognitive radio (CR) system is proposed. A secondary system sum rate maximization problem is formulated by jointly considering the base st…
SAGA: A Robust Self-Attention and Goal-Aware Anchor-based Planner for Safe UAV Autonomous Navigation
Junhao Wei, Yanxiao Li, Dexing Yao +9
Agile unmanned aerial vehicle (UAV) navigation in cluttered environments demands a planning architecture that is both computationally efficient and structurally expressive enough t…
GraphERE: Jointly Multiple Event-Event Relation Extraction via Graph-Enhanced Event Embeddings
Haochen Li, Di Geng
Events describe the state changes of entities. In a document, multiple events are connected by various relations (e.g., Coreference, Temporal, Causal, and Subevent). Therefore, obt…
STAR-RIS Aided Integrated Sensing, Computing, and Communication for Internet of Robotic Things
Haochen Li, Xidong Mu, Yuanwei Liu +2
A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) aided integrated sensing, computing, and communication (ISCC) Internet of Robotic Things…
Time-resolving PIV measurements and modal analysis of turbulent flow in a bench-scale hydrodynamic separator
Haochen Li
Effective stormwater treatment infrastructures are crucial for mitigating the adverse effects of runoff on urban water quality. However, designing cost-effective treatment systems…
Pinching Antenna Systems (PASS) for Cell-Free Communications
Haochen Li, Jiayi Lei, Cheng Zeng +3
A pinching antenna system (PASS) assisted cell-free communication system is proposed. A sum rate maximization problem under the BS power budget constraint and PA deployment constra…
TEeVTOL: Balancing Energy and Time Efficiency in eVTOL Aircraft Path Planning Across City-Scale Wind Fields
Songyang Liu, Shuai Li, Haochen Li +2
Electric vertical-takeoff and landing (eVTOL) aircraft, recognized for their maneuverability and flexibility, offer a promising alternative to our transportation system. However, t…
EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness
Yunxiao Zhang, Guanming Xiong, Haochen Li +1
Large Language Models (LLMs) have shown remarkable capabilities as AI agents. However, existing methods for enhancing LLM-agent abilities often lack a focus on data quality, leadin…
Operator-based machine learning framework for generalizable prediction of unsteady treatment dynamics in stormwater infrastructure
Mohamed Shatarah, Kai Liu, Haochen Li
Stormwater infrastructures are decentralized urban water-management systems that face highly unsteady hydraulic and pollutant loadings from episodic rainfall-runoff events. Accurat…
Energy-efficient Alternating Iterative Secure Structure of Maximizing Secrecy Rate for Directional Modulation Networks
Linlin Sun, Jiayu Li, Yu Zhang +6
In a directional modulation (DM) network, the issues of security and privacy have taken on an increasingly important role. Since the power allocation of confidential message and ar…
Automated Superconducting Qubit Characterisation Platform Based on a Modified 3D Printer
Haochen Li, Soe Gon Yee Thant, Rainer Dumke
Josephson Junctions are important components in superconducting qubits. It introduces anharmonicity to the energy level spacings of the qubit which allow us to identify two unique…
Pinching Antenna Systems for Integrated Sensing and Communications
Haochen Li, Ruikang Zhong, Jiayi Lei +1
Recently, the pinching antenna system (PASS) has attracted considerable attention due to their advantages in flexible deployment and reduction of signal propagation loss. In this w…
A Novel Sixth Order Energy-Conserved Method for Three-Dimensional Time-Domain Maxwell's Equations
Chaolong Jiang, Wenjun Cai, Yushun Wang +1
In this paper, a novel sixth order energy-conserved method is proposed for solving the three-dimensional time-domain Maxwell's equations. The new scheme preserves five discrete ene…
Turbulence Model Development based on a Novel Method Combining Gene Expression Programming with an Artificial Neural Network
Haochen Li, Fabian Waschkowski, Yaomin Zhao +1
Data-driven methods are widely used to develop physical models, but there still exist limitations that affect their performance, generalizability and robustness. By combining gene…
Reconfigurable Power Electronics Topologies
Haochen Li, Jonathan Shek
This paper presents two novel topologies for automatically transforming power converter topology from three-phase 3-level cascaded H-bridge to three-phase 2-level converter design.…
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Samuel Cahyawijaya, Peerat Limkonchotiwat, Tack Hwa Wong +45
While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedic…
Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting
Tianye Li, Qi Liu, Hao Li +15
Accurate global medium-range weather forecasting is fundamental to Earth system science. Most existing Transformer-based forecasting models adopt vision-centric architectures that…
Sparse Winograd Convolutional neural networks on small-scale systolic arrays
Feng Shi, Haochen Li, Yuhe Gao +2
The reconfigurability, energy-efficiency, and massive parallelism on FPGAs make them one of the best choices for implementing efficient deep learning accelerators. However, state-o…
A Polynomial-Decay and Pinhole-Imaging Whale Optimization Algorithm for UAV Relay Communication Deployment
Zhenhong Peng, Junhao Wei, Baili Lu +6
Unmanned aerial vehicle (UAV) relays deliver flexible, on-demand wireless coverage, but jointly tuning the position, altitude, transmit power and bandwidth of the relay is a non-co…
StableAML: Machine Learning for Behavioral Wallet Detection in Stablecoin Anti-Money Laundering on Ethereum
Luciano Juvinski, Haochen Li, Alessio Brini
The paper presents a machine‑learning system that uses tree‑ensemble models to identify suspicious stablecoin wallets on Ethereum, achieving higher detection performance than graph…
Prompt-based Graph Model for Joint Liberal Event Extraction and Event Schema Induction
Haochen Li, Di Geng
Events are essential components of speech and texts, describing the changes in the state of entities. The event extraction task aims to identify and classify events and find their…
Discrete line integral method for the Lorentz force system
Haochen Li, Yushun Wang
In this paper, we apply the Boole discrete line integral to solve the Lorentz force system which is written as a non-canonical Hamiltonian system. The method is exactly energy-cons…
CRB minimization for PASS Assisted ISAC
Haochen Li, Ruikang Zhong, Jiayi Lei +2
A multiple waveguide PASS assisted integrated sensing and communication (ISAC) system is proposed, where the base station (BS) is equipped with transmitting pinching antennas (PAs)…
On the Sum Rate and User Fairness of STAR-RIS Aided Communications
Haochen Li, Xidong Mu, Yuanwei Liu +2
A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) aided communication system is investigated. A robust joint beamforming design problem und…
A sixth order averaged vector field method
Haochen Li, Yushun Wang, Mengzhao Qin
In this paper, based on the theory of rooted trees and B-series, we propose the concrete formulas of the substitution law for the trees of order =5. With the help of the new substi…
GiFT: Gibbs Fine-Tuning for Code Generation
Haochen Li, Wanjin Feng, Xin Zhou +1
Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation. A key approach is self-training, where LLMs are iteratively trained on self-ge…
Continuum-Interaction-Driven Intelligence: Human-Aligned Neural Architecture via Crystallized Reasoning and Fluid Generation
Pengcheng Zhou, Zhiqiang Nie, Haochen Li
Current AI systems based on probabilistic neural networks, such as large language models (LLMs), have demonstrated remarkable generative capabilities yet face critical challenges i…
Landscape-Aware Bandit Hyper-Heuristics for Online Operator Selection in UAV Inspection Routing
Junhao Wei, Yanxiao Li, Yifu Zhao +8
UAV multi-site inspection often reduces to choosing a high-quality visiting order after target sites have been extracted from a map. This paper develops LA-BHH, a landscape-aware b…
Prompt-based Visual Alignment for Zero-shot Policy Transfer
Haihan Gao, Rui Zhang, Qi Yi +13
Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature ex…
Near-Field Integrated Sensing, Positioning, and Communication: A Downlink and Uplink Framework
Haochen Li, Zhaolin Wang, Xidong Mu +2
A near-field integrated sensing, positioning, and communication (ISPAC) framework is proposed, where a base station (BS) simultaneously serves multiple communication users and carr…
WASHH: An Anchor-Aware Whale-Guided Selection Hyper-Heuristic for Continuous Optimization and SVC Configuration
Yifu Zhao, Xiaofan Zou, Junhao Wei +9
Learning-assisted algorithm design often has to make reliable search decisions under small evaluation budgets, where committing to a single metaheuristic can be unreliable. We prop…
Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search
Haochen Li, Xin Zhou, Zhiqi Shen
In code search, the Generation-Augmented Retrieval (GAR) framework, which generates exemplar code snippets to augment queries, has emerged as a promising strategy to address the pr…
Detecting Financial Market Manipulation with Statistical Physics Tools
Haochen Li, Maria Polukarova, Carmine Ventre
We take inspiration from statistical physics to develop a novel conceptual framework for the analysis of financial markets. We model the order book dynamics as a motion of particle…
Merging of single-particle levels in finite Fermi systems
V. A. Khodel, J. W. Clark, Haochen Li +1
Properties of the distribution of single-particle levels adjacent to the Fermi surface in finite Fermi systems are studied, focusing on the case in which these levels are degenerat…
DNRSelect: Active Best View Selection for Deferred Neural Rendering
Dongli Wu, Haochen Li, Xiaobao Wei
Deferred neural rendering (DNR) is an emerging computer graphics pipeline designed for high-fidelity rendering and robotic perception. However, DNR heavily relies on datasets compo…
Rethinking Negative Pairs in Code Search
Haochen Li, Xin Zhou, Luu Anh Tuan +1
Recently, contrastive learning has become a key component in fine-tuning code search models for software development efficiency and effectiveness. It pulls together positive code s…
AeroTSBoost: Temporal-Statistical Boosting for Real-World UAV Telemetry Anomaly Mining
Junhao Wei, Haochen Li, Yanxiao Li +7
Mining anomalies from unmanned aerial vehicle (UAV) state-estimation logs is challenging because failures are sparse, temporally structured, and distributed across heterogeneous PX…
Exploring Representation-Level Augmentation for Code Search
Haochen Li, Chunyan Miao, Cyril Leung +4
Code search, which aims at retrieving the most relevant code fragment for a given natural language query, is a common activity in software development practice. Recently, contrasti…
Channel Estimation for Reconfigurable Intelligent Surface-Aided Multiuser Communication Systems Exploiting Statistical CSI of Correlated RIS-User Channels
Haochen Li, Zhiwen Pan, Bin Wang +2
Reconfigurable intelligent surface (RIS) is a promising candidate technology for the upcoming Sixth Generation (6G) communication system for its ability to manipulate the wireless…
Partitioned AVF methods
Wenjun Cai, Haochen Li, Yushun Wang
The classic second-order average vector field (AVF) method can exactly preserve the energy for Hamiltonian ordinary differential equations and partial differential equations. Howev…
SPDiffusion: Semantic Protection Diffusion Models for Multi-concept Text-to-image Generation
Yang Zhang, Rui Zhang, Xuecheng Nie +6
Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain mult…
A novel directly energy-preserving method for charged particle dynamics
Yexin Li, Ping Jiang, Haochen Li
In this paper, we apply the coordinate increment discrete gradient (CIDG) method to solve the Lorentz force system which can be written as a non-canonical Hamiltonian system. Then…
DA-Mamba: Learning Domain-Aware State Space Model for Global-Local Alignment in Domain Adaptive Object Detection
Haochen Li, Rui Zhang, Hantao Yao +5
Domain Adaptive Object Detection (DAOD) aims to transfer detectors from a labeled source domain to an unlabeled target domain. Existing DAOD methods employ multi-granularity featur…
Statistical CSI Based Beamforming for Reconfigurable Intelligent Surface Aided MISO Systems with Channel Correlation
Haochen Li, Zhiwen Pan, Bin Wang +2
Reconfigurable intelligent surface (RIS) is a promising candidate technology of the upcoming Sixth Generation (6G) communication system for its ability to provide unprecedented spe…
Gradient Information and Regularization for Gene Expression Programming to Develop Data-Driven Physics Closure Models
Fabian Waschkowski, Haochen Li, Abhishek Deshmukh +5
Learning accurate numerical constants when developing algebraic models is a known challenge for evolutionary algorithms, such as Gene Expression Programming (GEP). This paper intro…
Stepwise Schema-Guided Prompting Framework with Parameter Efficient Instruction Tuning for Multimedia Event Extraction
Xiang Yuan, Xinrong Chen, Haochen Li +4
Multimedia Event Extraction (MEE) has become an important task in information extraction research as news today increasingly prefers to contain multimedia content. Current MEE work…
STAR-RIS in Cognitive Radio Networks
Haochen Li, Yuanwei Liu, Xidong Mu +3
The development of sixth-generation (6G) communication technologies is confronted with the significant challenge of spectrum resource shortage. To alleviate this issue, we propose…
HonestAffinity: Leak-Aware Evaluation of Protein and Pocket Priors for Binding Affinity Prediction
Junhao Wei, Baili Lu, Zhenhong Peng +10
Sequence-based deep learning offers a scalable alternative to structure-based scoring for protein-ligand binding affinity prediction. However, progress is hard to interpret when ar…
Understand Then Memory: A Cognitive Gist-Driven RAG Framework with Global Semantic Diffusion
Pengcheng Zhou, Haochen Li, Zhiqiang Nie +4
Retrieval-Augmented Generation (RAG) effectively mitigates hallucinations in LLMs by incorporating external knowledge. However, the inherent discrete representation of text in exis…
A streamline upwind/Petrov-Galerkin method for the magnetic advection-diffusion problem
Haochen Li, Yangfan Luo, Jindong Wang +1
This paper presents the development and analysis of a streamline upwind/Petrov-Galerkin (SUPG) method for the magnetic advection-diffusion problem. A key feature of the method is a…
MCTS-KBQA: Monte Carlo Tree Search for Knowledge Base Question Answering
Guanming Xiong, Haochen Li, Wen Zhao
This study explores how to enhance the reasoning capabilities of large language models (LLMs) in knowledge base question answering (KBQA) by leveraging Monte Carlo Tree Search (MCT…
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
V Team, Wenyi Hong, Xiaotao Gu +94
We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depen…
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz +89
Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-language (VL) research. This often resu…