papers

Publications (47)

eess.SP2021

Deep Learning for Depression Recognition with Audiovisual Cues: A Review

Lang He, Mingyue Niu, Prayag Tiwari +9

With the acceleration of the pace of work and life, people have to face more and more pressure, which increases the possibility of suffering from depression. However, many patients…

cs.CL2026

PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models

Han Bao, Penghao Zhang, Yue Huang +9

Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to comprehend and reason abou…

cs.CV2022

NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition

Boyang Xia, Wenhao Wu, Haoran Wang +5

It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video re…

physics.chem-ph2026

Empowering Polymeric Materials Discovery by Artificial Intelligence

Chenyao Ma, Linda Zhang, Yuheng Chen +29

Polymeric materials underpin modern technologies spanning energy storage, microelectronics, healthcare and sustainable manufacturing. Yet their rational design remains exceptionall…

cs.LG2026

D-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market

Taijie Chen, Rui Su, Siyuan Feng +6

Ride-hailing platforms like DiDi Chuxing operate in highly dynamic environments where balancing driver supply and passenger demand is critical. Although driver-side subsidies serve…

cond-mat.mtrl-sci2025

Ultrafast Exciton-Polariton Transport and Relaxation in Halide Perovskite

Yuexing Xia, Yin Liang, Zhiyong Zhang +13

Halide perovskites offer a great platform for room-temperature exciton-polaritons (EPs) due to their strong oscillator strength and large exciton binding energy, promising applicat…

physics.optics2020

Ultralow Threshold Polariton Condensate in a Monolayer Semiconductor Microcavity at Room Temperature

Jiaxin Zhao, Rui Su, Antonio Fieramosca +7

Atomically thin transition metal dichalcogenides possess valley dependent functionalities that are usually available only at crogenic temperatures, constrained by various valley de…

physics.optics2021

Direct Measurement of a Non-Hermitian Topological Invariant in a Hybrid Light-Matter System

Rui Su, Eliezer Estrecho, DÄ brówka Biegańska +7

Topology is central to understanding and engineering materials that display robust physical phenomena immune to imperfections. Different topological phases of matter are characteri…

physics.optics2024

Perovskite topological exciton-polariton disclination laser at room temperature

Feng Jin, Subhaskar Mandal, Xutong Wang +2

Topologically nontrivial systems can be protected by band topology in momentum space, as seen in topological insulators and semimetals, or real-space topology, such as in lattice d…

cond-mat.str-el2023

Multifunctional magnetic oxide-MoS heterostructures on silicon

Allen Jian Yang, Liang Wu, Yanran Liu +9

Correlated oxides and related heterostructures are intriguing for developing future multifunctional devices by exploiting their exotic properties, but their integration with other…

physics.app-ph2018

Highly efficient visible colloidal lead-halide perovskite nanocrystal light-emitting diodes

Fei Yan, Jun Xing, Guichuan Xing +11

Lead-halide perovskites have been attracting attention for potential use in solid-state lighting. Following the footsteps of solar cells, the field of perovskite light-emitting dio…

physics.optics2022

Unveiling the Enhancement of Spontaneous Emission at Exceptional Points

Lydie Ferrier, Paul Bouteyre, Adi Pick +10

Exceptional points (EPs), singularities of non-Hermitian physics where complex spectral resonances degenerate, are one of the most exotic features of nonequilibrium open systems wi…

cond-mat.mtrl-sci2022

Atomic Origin of Annealing Embrittlement in Metallic Glasses

Rui Su, Shan Zhang, Xuefeng Zhang +3

An atomistic understanding of annealing embrittlement is a longstanding issue for metallic glasses, which is still lacking due to the insurmountable gap between the thermal history…

cs.AI2025

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Wanghan Xu, Yuhao Zhou, Yifan Zhou +104

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…

cs.MA2025

Swarm Intelligence Enhanced Reasoning: A Density-Driven Framework for LLM-Based Multi-Agent Optimization

Ying Zhu, Heng Zhou, Rui Su +2

Recently, many approaches, such as Chain-of-Thought (CoT) prompting and Multi-Agent Debate (MAD), have been proposed to further enrich Large Language Models' (LLMs) complex problem…

cond-mat.mes-hall2024

Trembling Motion of Exciton-Polaritons Close to the Rashba-Dresselhaus Regime

Wen Wen, Jie Liang, Huawen Xu +4

We report the experimental emulation of trembling quantum motion, or Zitterbewegung, of exciton polaritons in a perovskite microcavity at room temperature. By introducing liquid cr…

cs.LG2025

SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model

Xinghao Wang, Feng Liu, Rui Su +5

Recent advances in deep learning have revolutionized seismic monitoring, yet developing a foundation model that performs well across multiple complex tasks remains challenging, par…

physics.optics2024

Room temperature spin-layer locking of exciton-polariton nonlinearities

Jiaxin Zhao, Antonio Fieramosca, Kevin Dini +12

Recent advancements in transition metal dichalcogenides (TMDs) have unveiled exceptional optical and electronic characteristics, opened up new opportunities, and provided a unique…

cs.CV2021

SGE net: Video object detection with squeezed GRU and information entropy map

Rui Su, Wenjing Huang, Haoyu Ma +2

Recently, deep learning based video object detection has attracted more and more attention. Compared with object detection of static images, video object detection is more challeng…

cs.CV2025

Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain

Rui Su, Dong Xu, Luping Zhou +1

Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propos…

cs.CV2024

Fast Information Streaming Handler (FisH): A Unified Seismic Neural Network for Single Station Real-Time Earthquake Early Warning

Tianning Zhang, Feng Liu, Yuming Yuan +3

Existing EEW approaches often treat phase picking, location estimation, and magnitude estimation as separate tasks, lacking a unified framework. Additionally, most deep learning mo…

cond-mat.mes-hall2019

Observation of Exciton Polariton Condensation in a Perovskite Lattice at Room Temperature

Rui Su, Sanjib Ghosh, Sheng Liu +3

Bose-Einstein condensation in strongly correlated lattices provides the possibility to coherently generate macroscopic quantum states, which have attracted tremendous attention as…

cs.LG2026

KReF: Training-Free Retrieval for Long-Term Time-Series Forecasting and Predictive Uncertainty

Yang Zhang, Rui Su

Probabilistic long-term time-series forecasting commonly relies on trained models. Training-free conformal methods typically construct intervals around a pre-existing point forecas…

physics.optics2026

Optically reconfigurable canalization of exciton-polaritons in a non-hyperbolic perovskite

Jiahao Ren, Olha Bahrova, Feng Jin +5

The ability to steer polariton flow on-demand holds significant promise towards nanophotonic applications and photonic circuitry. Polariton canalization, exhibiting intrinsic colli…

cs.CV2025

Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization

Rui Su, Dong Xu, Luping Zhou +1

Spatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal localization. In this work, we propose a new progre…

cond-mat.mtrl-sci2023

Efficient and accurate simulation of vitrification in multi-component metallic liquids with neural-network potentials

Rui Su, Jieyi Yu, Pengfei Guan +1

Constructing accurate interatomic potential and overcoming the exponential growth of structural equilibration time are challenges to the atomistic investigations of the composition…

cs.LG2026

Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting

Fan Xu, Yuan Gao, Kun Wang +4

Probabilistic weather forecasting requires not only accurate trajectories, but calibrated distributions over plausible atmospheric futures. Recent data-driven systems have achieved…

physics.optics2026

Observation of polaritonic flat-band bound states in the continuum in a 2D magnet

Fuhuan Shen, Jiahao Ren, Zhiyi Yuan +5

Flat-band bound states in the continuum (BICs) are topological states with suppressed group velocity and robustness against radiation loss, offering a powerful platform for the exp…

physics.geo-ph2025

DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion

Feng Liu, Bao Deng, Rui Su +2

Surface wave dispersion curve inversion is crucial for estimating subsurface shear-wave velocity (vs), yet traditional methods often face challenges related to computational cost,…

physics.geo-ph2025

OpenSWI: A Massive-Scale Benchmark Dataset for Surface Wave Dispersion Curve Inversion

Feng Liu, Sijie Zhao, Xinyu Gu +8

Surface wave dispersion curve inversion plays a critical role in both shallow resource exploration and deep geological studies, yet it remains hindered by sensitivity to initial mo…

cs.CV2022

Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization

Weiqi Sun, Rui Su, Qian Yu +1

Weakly supervised temporal action localization (WTAL) aims to localize actions in untrimmed videos with only weak supervision information (e.g. video-level labels). Most existing m…

cs.LG2019

Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space

Zhou Fan, Rui Su, Weinan Zhang +1

In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor ne…

cond-mat.mes-hall2026

Beam canalization by a non-Abelian gauge field

Olha Bahrova, Jiahao Ren, Feng Jin +3

Hyperbolic and quasi-flat isofrequency contours (IFCs) are used for beam canalization and can be created by tilted Dirac points in photonic systems. Dirac points in microcavities a…

cond-mat.mtrl-sci2025

Linking Thermal History to Shear Band Interaction and Macroscopic Ductility in Metallic Glasses

Lechuan Sun, Shan Zhang, Bin Xu +3

Shear band propagation and interaction are critical to the mechanical performance of metallic glasses and are strongly governed by thermal history, yet their microscopic mechanisms…

cond-mat.mtrl-sci2019

An Accurate and Transferable Machine-Learning Interatomic Potential for Silicon

Lin Hu, Rui Su, Bing Huang +1

The development of modern ab initio methods has rapidly increased our understanding of physics, chemistry and materials science. Unfortunately, intensive ab initio calculations are…

cs.LG2026

Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling

Aihua Zhu, Rui Su, Qinglin Zhao +3

Diffusion probabilistic models have set a new standard for generative fidelity but are hindered by a slow iterative sampling process. A powerful training-free strategy to accelerat…

cs.GR2026

Vertex Features for Neural Global Illumination

Rui Su, Honghao Dong, Haojie Jin +3

Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. However, traditional feature…

physics.optics2026

Reconfigurable ultrafast perovskite polariton logic gates via nonlinear dynamics

Yuyang Zhang, Zhuoya Zhu, Xin Zeng +14

Exciton-polaritons provide a great platform for developing ultrafast all-optical logic gates for quantum and optical chips. However, progress toward practical polariton logic remai…

cond-mat.mtrl-sci2026

From Materials Database to Materials Bank: Assetizing Data for AI Driven Materials Innovation

Chenyao Ma, Di Zhang, Weibo Gong +9

Driven by high-throughput experimentation, computational modeling, and artificial intelligence (AI), materials data has expanded at an unprecedented rate. Conventional materials da…

cs.CV2022

3D-QueryIS: A Query-based Framework for 3D Instance Segmentation

Jiaheng Liu, Tong He, Honghui Yang +6

Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of…

cond-mat.mtrl-sci2017

Room Temperature Polariton Lasing in All-Inorganic Perovskites

Rui Su, Carole Diederichs, Jun Wang +6

Polariton lasing is the coherent emission arising from a macroscopic polariton condensate first proposed in 1996. Over the past two decades, polariton lasing has been demonstrated…

cond-mat.mtrl-sci2025

Turing Pattern Engineering Enables Kinetically Ultrastable yet Ductile Metallic Glasses

Huanrong Liu, Qingan Li, Shan Zhang +3

Enhancing the kinetic stability of glasses often necessitates deepening thermodynamic stability, which typically compromises ductility due to increased structural rigidity. Decoupl…

physics.geo-ph2025

Deep Reparameterization for Full Waveform Inversion: Architecture Benchmarking, Robust Inversion, and Multiphysics Extension

Feng Liu, Yaxing Li, Rui Su +2

Full waveform inversion (FWI) is a high-resolution subsurface imaging technique, but its effectiveness is limited by challenges such as noise contamination, sparse acquisition, and…

cs.AI2023

FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead

Kang Chen, Tao Han, Junchao Gong +11

We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI). Different from existing data-driven weather forecast m…

physics.optics2026

Dynamic topological exciton-polaritons enabling ultrafast logic operations

Feng Jin, Hao Zheng, Zhe Zhang +7

Topological active materials have emerged as powerful paradigm bridging the discovery of exotic topological phases of matter with the development of functional topological devices.…

physics.optics2024

Observation of perovskite topological valley exciton-polaritons at room temperature

Feng Jin, Subhaskar Mandal, Zhenhan Zhang +7

Topological exciton-polaritons are a burgeoning class of topological photonic systems distinguished by their hybrid nature as part-light, part-matter quasiparticles. Their further…

physics.optics2020

Optical Control of Topological Polariton Phase in a Perovskite Lattice

Rui Su, Sanjib Ghosh, Timothy C. H. Liew +1

Strong light-matter interaction enriches topological photonics by dressing light with matter, which provides the possibility to realize tuneable topological devices with immunity t…