papers

Publications (277)

cs.LG2025

Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models

Huifeng Yin, Yu Zhao, Minghao Wu +9

Large Reasoning Models(LRMs) such as OpenAI o1 and DeepSeek-R1 have shown remarkable reasoning capabilities by scaling test-time compute and generating long Chain-of-Thought(CoT).…

cs.CL2022

MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion

Yu Zhao, Xiangrui Cai, Yike Wu +4

Multimodal knowledge graph completion (MKGC) aims to predict missing entities in MKGs. Previous works usually share relation representation across modalities. This results in mutua…

physics.soc-ph2025

Identifying polycentric urban structure using the minimum cycle basis of road network as building blocks

Yuanbiao Li, Tingyu Wang, Yu Zhao +1

In a graph, the minimum cycle bases are a set of linearly independent cycles that can be used to represent any cycle within that cycle space of graph. These bases are useful in var…

cs.LG2024

Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis

Sijie Mai, Yu Zhao, Ying Zeng +2

Multimodal sentiment analysis aims to effectively integrate information from various sources to infer sentiment, where in many cases there are no annotations for unimodal labels. T…

cs.CV2026

ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection

Huangsen Cao, Hongkang Chu, Yuxi Li +6

The rapid advancement of generative models has made synthetic images increasingly realistic, challenging reliable detection. Existing methods are often limited to end-to-end classi…

physics.ins-det2026

Design and First Results of COFFEE3: A 55nm HVCMOS Pixel Sensor Prototype for High-Energy Physics Applications

Xiaomin Wei, Zijun Xu, Weiguo Lu +25

Motivated by the stringent requirements of the Upstream Pixel (UP) tracker in the LHCb Upgrade II and the Inner Tracking detector (ITK) of the Circular Electron Positron Collider,…

cs.CL2025

Utilizing Large Language Models for Information Extraction from Real Estate Transactions

Yu Zhao, Haoxiang Gao, Jinghan Cao +1

Real estate sales contracts contain crucial information for property transactions, but manual data extraction can be time-consuming and error-prone. This paper explores the applica…

cs.MM2024

Contrast then Memorize: Semantic Neighbor Retrieval-Enhanced Inductive Multimodal Knowledge Graph Completion

Yu Zhao, Ying Zhang, Baohang Zhou +3

A large number of studies have emerged for Multimodal Knowledge Graph Completion (MKGC) to predict the missing links in MKGs. However, fewer studies have been proposed to study the…

cs.CL2026

Slang Context-based Inference Enhancement via Greedy Search-Guided Chain-of-Thought Prompting

Jinghan Cao, Qingyang Ren, Xiangyun Chen +3

Slang interpretation has been a challenging downstream task for Large Language Models (LLMs) as the expressions are inherently embedded in contextual, cultural, and linguistic fram…

cs.LG2023

Taming Gradient Variance in Federated Learning with Networked Control Variates

Xingyan Chen, Yaling Liu, Huaming Du +2

Federated learning, a decentralized approach to machine learning, faces significant challenges such as extensive communication overheads, slow convergence, and unstable improvement…

cs.AI2024

Multi-Scale Subgraph Contrastive Learning

Yanbei Liu, Yu Zhao, Xiao Wang +2

Graph-level contrastive learning, aiming to learn the representations for each graph by contrasting two augmented graphs, has attracted considerable attention. Previous studies usu…

cs.DC2023

Workload Distribution with Rateless Encoding: A Low-Latency Computation Offloading Method within Edge Networks

Zhongfu Guo, Xinsheng Ji, Wei You +3

This paper introduces REDC, a comprehensive strategy for offloading computational tasks within mobile Edge Networks (EN) to Distributed Computing (DC) after Rateless Encoding (RE).…

cs.CL2024

Training-free LLM-generated Text Detection by Mining Token Probability Sequences

Yihuai Xu, Yongwei Wang, Yifei Bi +4

Large language models (LLMs) have demonstrated remarkable capabilities in generating high-quality texts across diverse domains. However, the potential misuse of LLMs has raised sig…

cs.MM2024

SpeechEE: A Novel Benchmark for Speech Event Extraction

Bin Wang, Meishan Zhang, Hao Fei +5

Event extraction (EE) is a critical direction in the field of information extraction, laying an important foundation for the construction of structured knowledge bases. EE from tex…

cs.CL2024

Tele-FLM Technical Report

Xiang Li, Yiqun Yao, Xin Jiang +17

Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications. However, there is a notable p…

physics.acc-ph2022

Multi-objective optimization of longitudinal injection based on a multi-frequency RF system for fourth-generation storage ring-based light sources

Weihang Liu, Yi Jiao, Yu Zhao +3

In the fourth-generation storage ring light sources (4GLSs), associated with the extremely strong nonlinearities inherent in the multi-bend achromat design, the dynamic acceptance…

cs.LG2024

Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decoupling

Xingyan Chen, Tian Du, Mu Wang +5

Federated learning, as a promising distributed learning paradigm, enables collaborative training of a global model across multiple network edge clients without the need for central…

cs.CL2020

Connecting Embeddings for Knowledge Graph Entity Typing

Yu Zhao, Anxiang Zhang, Ruobing Xie +2

Knowledge graph (KG) entity typing aims at inferring possible missing entity type instances in KG, which is a very significant but still under-explored subtask of knowledge graph c…

eess.SY2016

Designing Distributed Fixed-Time Consensus Protocols for Linear Multi-Agent Systems Over Directed Graphs

Yu Zhao, Yongfang Liu, Guanrong Chen

This technical note addresses the distributed fixed-time consensus protocol design problem for multi-agent systems with general linear dynamics over directed communication graphs.…

cs.IR2024

A Survey of Retrieval Algorithms in Ad and Content Recommendation Systems

Yu Zhao, Fang Liu

This survey examines the most effective retrieval algorithms utilized in ad recommendation and content recommendation systems. Ad targeting algorithms rely on detailed user profile…

cs.AI2022

Medical Dialogue Response Generation with Pivotal Information Recalling

Yu Zhao, Yunxin Li, Yuxiang Wu +5

Medical dialogue generation is an important yet challenging task. Most previous works rely on the attention mechanism and large-scale pretrained language models. However, these met…

cs.CE2025

Identifying Evidence Subgraphs for Financial Risk Detection via Graph Counterfactual and Factual Reasoning

Huaming Du, Lei Yuan, Qing Yang +6

Company financial risks pose a significant threat to personal wealth and national economic stability, stimulating increasing attention towards the development of efficient andtimel…

cs.CV2022

Differentiable Channel Sparsity Search via Weight Sharing within Filters

Yu Zhao, Chung-Kuei Lee

In this paper, we propose the differentiable channel sparsity search (DCSS) for convolutional neural networks. Unlike traditional channel pruning algorithms which require users to…

cs.SE2023

How to get better embeddings with code pre-trained models? An empirical study

Yu Zhao, Lina Gong, Haoxiang Zhang +2

Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the e…

cs.CV2025

Generating Vision-Language Navigation Instructions Incorporated Fine-Grained Alignment Annotations

Yibo Cui, Liang Xie, Yu Zhao +2

Vision-Language Navigation (VLN) enables intelligent agents to navigate environments by integrating visual perception and natural language instructions, yet faces significant chall…

cs.CV2026

Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models

Aaron Branson Cigres Li, Zhaowei Wang, Yu Zhao +9

Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate r…

cs.IR2026

Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation

Zixuan Wang, Yuhong Chen, Yuxuan Zhu +10

Industrial recommenders increasingly adopt the pretrain-then-transfer paradigm, yet behavioral distribution drift raises two questions: what to learn from behavior sequences, and h…

math.AG2023

Derived Blow-ups and Birational Geometry of Nested Quiver Varieties

Yu Zhao

Given a quiver, Nakajima introduced the quiver variety and the Hecke correspondence, which is a closed subvariety of Cartesian products of quiver varieties. In this paper, we consi…

cs.AI2026

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

Yu Zhao, Zekun Zhang, Fan Jiang +6

Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm. Howeve…

cs.CL2026

CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification

Chenshuo Pan, Yu Zhao, Jie Zhang +7

Table reasoning remains challenging for large language models (LLMs), particularly in tasks that require multi-step inference over long and structured tables. Existing approaches p…

cond-mat.mtrl-sci2018

Electrochemical solid-state amorphization in the immiscible Cu-Li system: Size matters

Muhua Sun, Jiake Wei, Zhi Xu +4

As a typical immiscible binary system, copper (Cu) and lithium (Li) show no alloying and chemical intermixing under normal circumstances. A notable example that takes advantages of…

cs.CL2025

The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks

Minghao Wu, Weixuan Wang, Sinuo Liu +7

As large language models (LLMs) continue to advance in linguistic capabilities, robust multilingual evaluation has become essential for promoting equitable technological progress.…

cs.CL2025

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language Models

Bo Zeng, Chenyang Lyu, Sinuo Liu +14

Instruction-following capability has become a major ability to be evaluated for Large Language Models (LLMs). However, existing datasets, such as IFEval, are either predominantly m…

cs.AI2021

GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph

Yunxin Li, Yu Zhao, Baotian Hu +5

Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters. The typic…

cs.CL2021

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Ke Wang, Yangbin Shi, Jiayi Wang +3

Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT). Traditionally, a QE system accepts the original source text and translation from a blac…

q-fin.RM2026

A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data and LLMs Perspective

Huaming Du, Cancan Feng, Yuqian Lei +5

Enterprise financial risk analysis aims at predicting the future financial risk of enterprises. Due to its wide and significant application, enterprise financial risk analysis has…

cs.LG2026

Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits

Andreas Grivas, Lorenzo Loconte, Emile van Krieken +6

Multi-token prediction (MTP) is a prominent strategy to significantly speed up generation in large language models (LLMs), especially in byte-level LLMs, which are tokeniser-free b…

cs.DM2015

Polynomial bounds for decoupling, with applications

Ryan O'Donnell, Yu Zhao

Let f(x) = f(x_1, ..., x_n) = \sum_{|S| <= k} a_S \prod_{i \in S} x_i be an n-variate real multilinear polynomial of degree at most k, where S \subseteq [n] = {1, 2, ..., n}. For i…

astro-ph.GA2025

A Composite Broad-Line Region in SDSS J1609+4902: a Double-Peaked Disk component and a Gaussian Component

Jiancheng Wu, Qingwen Wu, Chen Hu +6

The profiles of broad emission lines in active galactic nuclei (AGNs) provide critical insights into the geometry and kinematics of the broad-line region (BLR), which in turn influ…

cond-mat.str-el2023

Symmetry Fractionalized (Irrationalized) Fusion Rules and Two Domain-Wall Verlinde Formulae

Yu Zhao, Hongyu Wang, Yuting Hu +1

We investigate the composite systems consisting of topological orders separated by gapped domain walls. We derive a pair of domain-wall Verlinde formulae, that elucidate the connec…

cs.CL2025

Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering

Xinying Qian, Ying Zhang, Yu Zhao +3

Temporal Knowledge Graph Question Answering (TKGQA) aims to answer time-sensitive questions by leveraging factual information from Temporal Knowledge Graphs (TKGs). While previous…

math.NA2020

A unified structure preserving scheme for a multi-species model with a gradient flow structure and nonlocal interactions via singular kernels

Yong Zhang, Yu Zhao, Zhennan Zhou

In this paper, we consider a nonlinear and nonlocal parabolic model for multi-species ionic fluids and introduce a semi-implicit finite volume scheme, which is second order accurat…

cs.LG2018

A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification

Ke Ren, Haichuan Yang, Yu Zhao +4

The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a f…

cs.AI2026

Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation

Guining Cao, Jiaxin Peng, Chu Zeng +3

Current reinforcement learning(RL) methods are broadly applicable and powerful in verifiable settings where scalar rewards can be provided. However, in open-ended generation tasks,…

cs.CL2023

Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation

Ke Wang, Xin Ge, Jiayi Wang +2

Machine translation technology has made great progress in recent years, but it cannot guarantee error free results. Human translators perform post editing on machine translations t…

cs.CV2022

Improving Human-Object Interaction Detection via Phrase Learning and Label Composition

Zhimin Li, Cheng Zou, Yu Zhao +2

Human-Object Interaction (HOI) detection is a fundamental task in high-level human-centric scene understanding. We propose PhraseHOI, containing a HOI branch and a novel phrase bra…

eess.SY2013

Distributed average tracking for multiple reference signals with general linear dynamics

Yu Zhao, Zhisheng Duan, Zhongkui Li

This technical note studies the distributed average tracking problem for multiple time-varying signals with general linear dynamics, whose reference inputs are nonzero and not avai…

cs.CL2025

Training Report of TeleChat3-MoE

Xinzhang Liu, Chao Wang, Zhihao Yang +51

TeleChat3-MoE is the latest series of TeleChat large language models, featuring a Mixture-of-Experts (MoE) architecture with parameter counts ranging from 105 billion to over one t…

math.AG2020

A Serre Relation in the -theoretic Hall algebra of surfaces

Junyao Peng, Yu Zhao

We prove a Serre relation in the -theoretic Hall algebra of surfaces constructed by Kapranov-Vasserot and the second author.

cs.CL2025

MDEval: Evaluating and Enhancing Markdown Awareness in Large Language Models

Zhongpu Chen, Yinfeng Liu, Long Shi +3

Large language models (LLMs) are expected to offer structured Markdown responses for the sake of readability in web chatbots (e.g., ChatGPT). Although there are a myriad of metrics…

cs.CL2023

Synslator: An Interactive Machine Translation Tool with Online Learning

Jiayi Wang, Ke Wang, Fengming Zhou +5

Interactive machine translation (IMT) has emerged as a progression of the computer-aided translation paradigm, where the machine translation system and the human translator collabo…

cs.IT2026

Spatio-Temporal Attention Enhanced Multi-Agent DRL for UAV-Assisted Wireless Networks with Limited Communications

Che Chen, Lanhua Li, Shimin Gong +3

In this paper, we employ multiple UAVs to accelerate data transmissions from ground users (GUs) to a remote base station (BS) via the UAVs' relay communications. The UAVs' intermit…

cs.LG2025

Towards Comprehensive Information-theoretic Multi-view Learning

Long Shi, Yunshan Ye, Wenjie Wang +4

Information theory has inspired numerous advancements in multi-view learning. Most multi-view methods incorporating information-theoretic principles rely an assumption called multi…

eess.SP2022

Fast Electromagnetic Validations of Large-Scale Digital Coding Metasurfaces Accelerated by Recurrence Rebuild and Retrieval Method

Yu Zhao, Shang Xiang, Long Li

The recurrence rebuild and retrieval method (R3M) is proposed in this paper to accelerate the electromagnetic (EM) validations of large-scale digital coding metasurfaces (DCMs). R3…

cs.CL2025

T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

Jie Zhang, Changzai Pan, Kaiwen Wei +12

Extensive research has been conducted to explore the capabilities of large language models (LLMs) in table reasoning. However, the essential task of transforming tables information…

stat.ME2025

On the peak height distribution of non-stationary Gaussian random fields: 1D general covariance and scale space

Yu Zhao, Dan Cheng, Samuel Davenport +1

We study the peak height distribution of certain non-stationary Gaussian random fields. The explicit peak height distribution of smooth, non-stationary Gaussian processes in 1D wit…

cs.RO2024

Harnessing with Twisting: Single-Arm Deformable Linear Object Manipulation for Industrial Harnessing Task

Xiang Zhang, Hsien-Chung Lin, Yu Zhao +1

Wire-harnessing tasks pose great challenges to be automated by the robot due to the complex dynamics and unpredictable behavior of the deformable wire. Traditional methods, often r…

cond-mat.str-el2025

Symmetry-Enriched Topological Phases and Their Gauging: A String-Net Model Realization

Nianrui Fu, Yu Zhao, Yidun Wan

We present a systematic framework for constructing exactly-solvable lattice models of symmetry-enriched topological (SET) phases based on an enlarged version of the string-net mode…

cs.LG2023

Causal conditional hidden Markov model for multimodal traffic prediction

Yu Zhao, Pan Deng, Junting Liu +2

Multimodal traffic flow can reflect the health of the transportation system, and its prediction is crucial to urban traffic management. Recent works overemphasize spatio-temporal c…

physics.optics2021

A Spontaneously Formed Plasmonic-MoTe2 Hybrid Platform for Ultrasensitive Raman Enhancement

Li Tao, Zhiyong Li, Kun Chen +10

To develop highly sensitive, stable and repeatable surface-enhanced Raman scattering (SERS) substrates is crucial for analytical detection, which is a challenge for traditional met…

astro-ph.HE2023

Time-dependent global simulations of a thin accretion disc: the effects of magnetically-driven winds on thermal instability

Yu Zhao, Xiao-Hong Yang, Li Xue +1

According to the standard thin disc theory, it is predicted that the radiation-pressure-dominated inner region of a thin disc is thermally unstable, while observations suggest that…

math-ph2022

On the equilibrium of the Poisson-Nernst-Planck-Bikermann model equipping with the steric and correlation effects

Jian-Guo Liu, Yijia Tang, Yu Zhao

The Poisson-Nernst-Planck-Bikermann (PNPB) model, in which the ions and water molecules are treated as different species with non-uniform sizes and valences with interstitial voids…

stat.ME2023

An approximation to peak detection power using Gaussian random field theory

Yu Zhao, Dan Cheng, Armin Schwartzman

We study power approximation formulas for peak detection using Gaussian random field theory. The approximation, based on the expected number of local maxima above the threshold

cs.NI2023

Raptor Encoding for Low-Latency Concurrent Multi-PDU Session Transmission with Security Consideration in B5G Edge Network

Zhongfu Guo, Xinsheng Ji, Wei You +4

In B5G edge networks, end-to-end low-latency and high-reliability transmissions between edge computing nodes and terminal devices are essential. This paper investigates the queue-a…

cs.CL2024

RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL

Zhenhe Wu, Zhongqiu Li, Jie Zhang +7

Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task. Previous works generally focus on using exclusive SQL generat…

cs.CV2023

Generating Visual Spatial Description via Holistic 3D Scene Understanding

Yu Zhao, Hao Fei, Wei Ji +4

Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical v…

cs.CV2025

MIRAGE: A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence

Chonghan Liu, Haoran Wang, Felix Henry +4

Spatial perception and reasoning are core components of human cognition, encompassing object recognition, spatial relational understanding, and dynamic reasoning. Despite progress…

cs.IR2026

Compress, Cross and Scale: Multi-Level Compression Cross Networks for Efficient Scaling in Recommender Systems

Heng Yu, Xiangjun Zhou, Jie Xia +4

Modeling high-order feature interactions efficiently is a central challenge in click-through rate and conversion rate prediction. Modern industrial recommender systems are predomin…

physics.ins-det2022

Timing performance simulation for 3D 4H-SiC detector

Yuhang Tan, Tao Yang, Kai Liu +14

To meet high radiation challenge for detectors in future high-energy physics, a novel 3D 4H-SiC detector was investigated. SiC detectors could potentially operate in radiation hars…

cs.CL2025

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

Nathan Godey, Alessio Devoto, Yu Zhao +4

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths…

physics.acc-ph2026

High-Harmonic Coherent Pulse Generation in a Storage Ring Using Multiple-Echo-Enabled Harmonic Generation

Weihang Liu, Yu Zhao, Weilun Qin +3

Fourth-generation storage-ring light sources have achieved transverse emittances approaching the diffraction limit at x-ray wavelengths, while their longitudinal coherence remains…

cs.AI2026

Difficulty-Estimated Policy Optimization

Yu Zhao, Fan Jiang, Tianle Liu +4

Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Opt…

cs.MM2019

SmartBullets: A Cloud-Assisted Bullet Screen Filter based on Deep Learning

Haoran Niu, Jiangnan Li, Yu Zhao

Bullet-screen is a technique that enables the website users to send real-time comment `bullet' cross the screen. Compared with the traditional review of a video, bullet-screen prov…

cs.CL2024

Analysing The Impact of Sequence Composition on Language Model Pre-Training

Yu Zhao, Yuanbin Qu, Konrad Staniszewski +5

Most language model pre-training frameworks concatenate multiple documents into fixed-length sequences and use causal masking to compute the likelihood of each token given its cont…

cs.CL2022

An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

Yuxiang Wu, Yu Zhao, Baotian Hu +3

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model tha…

cs.IT2012

The Han-Kobayashi Region for a Class of Gaussian Interference Channels with Mixed Interference

Yu Zhao, Fangfang Zhu, Biao Chen

A simple encoding scheme based on Sato's non-naïve frequency division is proposed for a class of Gaussian interference channels with mixed interference. The achievable region is s…

cs.HC2025

StratIncon Detector: Analyzing Strategy Inconsistencies Between Real-Time Strategy and Preferred Professional Strategy in MOBA Esports

Ruofei Ma, Yu Zhao, Yuheng Shao +2

MOBA (Multiplayer Online Battle Arena) games require a delicate interplay of strategic planning and real-time decision-making, particularly in professional esports, where players e…

cs.LG2018

A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria

Yu Zhao, Zhenhui Shi, Jingyang Zhang +2

Multiple query criteria active learning (MQCAL) methods have a higher potential performance than conventional active learning methods in which only one criterion is deployed for sa…

cs.RO2025

DW-A-PRM: A Dynamic Weighted Planner

Siyuan Wang, Shuyi Zhang, Zhen Tian +3

Robot path planning plays a pivotal role in enabling autonomous systems to navigate safely and efficiently in complex and uncertain environments. Despite extensive research on clas…

eess.IV2022

Shuffle Instances-based Vision Transformer for Pancreatic Cancer ROSE Image Classification

Tianyi Zhang, Youdan Feng, Yunlu Feng +6

The rapid on-site evaluation (ROSE) technique can signifi-cantly accelerate the diagnosis of pancreatic cancer by im-mediately analyzing the fast-stained cytopathological images. C…

cs.AI2026

LifeBench: A Benchmark for Long-Horizon Multi-Source Memory

Zihao Cheng, Weixin Wang, Yu Zhao +15

Long-term memory is fundamental for personalized agents capable of accumulating knowledge, reasoning over user experiences, and adapting across time. However, existing memory bench…

physics.chem-ph2020

The Lightest 2D Nanomaterial: Freestanding Ultrathin Li Nanosheets by in-situ Electron Microscopy

Muhua Sun, Nore Stolte, Jianlin Wang +7

Lithium (Li) is the simplest metal and the lightest solid element. Here we report the first demonstration of controlled growth of two-dimensional (2D) ultrathin Li nanosheets with…

math.AG2019

On the -theoretic Hall algebra of a surface

Yu Zhao

In this paper, we define the -theoretic Hall algebra for -dimensional coherent sheaves on a smooth projective surface, prove that the algebra is associative and construct a h…

math.NA2024

Efficient bound preserving and asymptotic preserving semi-implicit schemes for the fast reaction-diffusion system

Yu Zhao, Zhennan Zhou

We consider a special type of fast reaction-diffusion systems in which the coefficients of the reaction terms of the two substances are much larger than those of the diffusion term…

cond-mat.str-el2026

Anyon Condensation In Symmetry-Enriched Topological Phases: -Grading of Multifusion Categories

Nianrui Fu, Siyuan Wang, Yu Zhao +1

Although anyon condensation is a standard mechanism for relating topological orders, anyon condensation in symmetry-enriched topological (SET) phases is more intricate because the…

cond-mat.str-el2025

Nonlinear Symmetry-Fragmentation of Nonabelian Anyons In Symmetry-Enriched Topological Phases: A String-Net Model Realization

Nianrui Fu, Siyuan Wang, Yu Zhao +1

Symmetry-enriched topological (SET) phases combine intrinsic topological order with global symmetries, giving rise to novel symmetry phenomena. While SET phases with Abelian anyons…

cs.AI2024

Next-Generation Simulation Illuminates Scientific Problems of Organised Complexity

Cheng Wang, Chuwen Wang, Wang Zhang +4

As artificial intelligence becomes increasingly prevalent in scientific research, data-driven methodologies appear to overshadow traditional approaches in resolving scientific prob…

cond-mat.str-el2026

Non-Abelian Particle-Loop, Fracton, and Planon Condensation in Cage-Net Models

Yifei Wang, Yu Zhao, Yingcheng Li +2

We present a framework for non-Abelian p-loop, fracton, and planon condensation in 3+1 dimensions by constructing extended cage-net fracton models using decoupled layers of the Hu-…

cs.CV2023

CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification

Tianyi Zhang, Zhiling Yan, Chunhui Li +5

In pathology image analysis, obtaining and maintaining high-quality annotated samples is an extremely labor-intensive task. To overcome this challenge, mixing-based methods have em…

cs.CV2018

Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN)

Yu Zhao, Xiang Li, Wei Zhang +5

Simultaneous modeling of the spatio-temporal variation patterns of brain functional network from 4D fMRI data has been an important yet challenging problem for the field of cogniti…

astro-ph.GA2025

Supermassive Black Holes with High Accretion Rates in Active Galactic Nuclei. XV. Reverberation Mapping of Mg II Emission Lines

Hua-Rui Bai, Pu Du, Chen Hu +25

As the 15th paper in a series reporting on a large reverberation mapping (RM) campaign of super-Eddington accreting massive black holes (SEAMBHs) in active galactic nuclei (AGNs),…

eess.IV2023

WATUNet: A Deep Neural Network for Segmentation of Volumetric Sweep Imaging Ultrasound

Donya Khaledyan, Thomas J. Marini, Avice OConnell +6

Objective. Limited access to breast cancer diagnosis globally leads to delayed treatment. Ultrasound, an effective yet underutilized method, requires specialized training for sonog…

cs.CV2025

DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Models

Jiarui Wang, Huiyu Duan, Juntong Wang +8

With the rapid advancement of generative models, the realism of AI-generated images has significantly improved, posing critical challenges for verifying digital content authenticit…

cs.IR2025

Mobile Gamer Lifetime Value Prediction via Objective Decomposition and Reconstruction

Tianwei Li, Yu Zhao, Yunze Li +1

For Internet platforms operating real-time bidding (RTB) advertising service, a comprehensive understanding of user lifetime value (LTV) plays a pivotal role in optimizing advertis…

cs.CL2022

TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task

Xin Ge, Ke Wang, Jiayi Wang +4

This paper describes the joint submission of Alibaba and Soochow University, TSMind, to the WMT 2022 Shared Task on Translation Suggestion (TS). We participate in the English-Germa…

cs.LG2026

Traceable Latent Variable Discovery Based on Multi-Agent Collaboration

Huaming Du, Tao Hu, Yijie Huang +5

Revealing the underlying causal mechanisms in the real world is crucial for scientific and technological progress. Despite notable advances in recent decades, the lack of high-qual…

cs.RO2025

CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence

Yu Zhao, Huxian Liu, Xiang Chen +3

Physical intelligence holds immense promise for advancing embodied intelligence, enabling robots to acquire complex behaviors from demonstrations. However, achieving generalization…

cs.CL2025

Noiser: Bounded Input Perturbations for Attributing Large Language Models

Mohammad Reza Ghasemi Madani, Aryo Pradipta Gema, Gabriele Sarti +3

Feature attribution (FA) methods are common post-hoc approaches that explain how Large Language Models (LLMs) make predictions. Accordingly, generating faithful attributions that r…

cs.RO2025

Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V

Peiyuan Zhi, Zhiyuan Zhang, Yu Zhao +6

Autonomous robot navigation and manipulation in open environments require reasoning and replanning with closed-loop feedback. In this work, we present COME-robot, the first closed-…

cs.RO2023

Learning from Local Experience: Informed Sampling Distributions for High Dimensional Motion Planning

Keita Kobashi, Changhao Wang, Yu Zhao +2

This paper presents a sampling-based motion planning framework that leverages the geometry of obstacles in a workspace as well as prior experiences from motion planning problems. P…