Publications (60)
Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
Rui Ye, Jingyi Chai, Xiangrui Liu +3
Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentr…
GPA-Net:No-Reference Point Cloud Quality Assessment with Multi-task Graph Convolutional Network
Ziyu Shan, Qi Yang, Rui Ye +4
With the rapid development of 3D vision, point cloud has become an increasingly popular 3D visual media content. Due to the irregular structure, point cloud has posed novel challen…
X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
Rui Ye, Xiangrui Liu, Qimin Wu +4
LLM-based multi-agent systems (MAS) extend the capabilities of single LLMs by enabling cooperation among multiple specialized agents. However, most existing MAS frameworks rely on…
AMSNet: Netlist Dataset for AMS Circuits
Zhuofu Tao, Yichen Shi, Yiru Huo +8
Today's analog/mixed-signal (AMS) integrated circuit (IC) designs demand substantial manual intervention. The advent of multimodal large language models (MLLMs) has unveiled signif…
FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning
Rui Ye, Zhenyang Ni, Chenxin Xu +3
One of the key challenges in federated learning (FL) is local data distribution heterogeneity across clients, which may cause inconsistent feature spaces across clients. To address…
Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models
Rui Ye, Rui Ge, Yuchi Fengting +3
Federated instruction tuning enables multiple clients to collaboratively fine-tune a shared large language model (LLM) that can follow humans' instructions without directly sharing…
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server
Wenhao Wang, Xiaoyu Liang, Rui Ye +3
The success of large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. However, this practice raises privacy concerns due to the memorizat…
High Q and high gradient performance of the first medium-temperature baking 1.3 GHz cryomodule
Jiyuan Zhai, Weimin Pan, Feisi He +36
World's first 1.3 GHz cryomodule containing eight 9-cell superconducting radio-frequency (RF) cavities treated by medium-temperature furnace baking (mid-T bake) was developed, asse…
WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking
Zhengwei Tao, Haiyang Shen, Baixuan Li +11
Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables…
CloudMamba: Grouped Selective State Spaces for Point Cloud Analysis
Kanglin Qu, Pan Gao, Qun Dai +3
Due to the long-range modeling ability and linear complexity property, Mamba has attracted considerable attention in point cloud analysis. Despite some interesting progress, relate…
Observation of flat-band and band transition in the synthetic space
Guangzhen Li, Luojia Wang, Rui Ye +4
Constructions of synthetic lattices in photonics attract growingly attentions for exploring interesting physics beyond the geometric dimensionality, among which modulated ring reso…
MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems
Rui Ye, Keduan Huang, Qimin Wu +17
LLM-based multi-agent systems (MAS) have demonstrated significant potential in enhancing single LLMs to address complex and diverse tasks in practical applications. Despite conside…
Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review
Rui Ye, Xianghe Pang, Jingyi Chai +6
Scholarly peer review is a cornerstone of scientific advancement, but the system is under strain due to increasing manuscript submissions and the labor-intensive nature of the proc…
Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
Rui Ye, Yaxin Du, Zhenyang Ni +2
In federated learning (FL), data heterogeneity is one key bottleneck that causes model divergence and limits performance. Addressing this, existing methods often regard data hetero…
SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?
Jingyi Chai, Shuo Tang, Rui Ye +8
The rapid advancements of AI agents have ignited the long-held ambition of leveraging them to accelerate scientific discovery. Achieving this goal requires a deep understanding of…
Learn What You Need in Personalized Federated Learning
Kexin Lv, Rui Ye, Xiaolin Huang +2
Personalized federated learning aims to address data heterogeneity across local clients in federated learning. However, current methods blindly incorporate either full model parame…
Structure-Aware Corpus Construction and User-Perception-Aligned Metrics for Large-Language-Model Code Completion
Dengfeng Liu, Jucai Zhai, Xiaoguang Jiang +8
Code completion technology based on large language model has significantly improved the development efficiency of programmers. However, in practical applications, there remains a g…
MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning
Baoquan Zhang, Xutao Li, Shanshan Feng +2
Few-Shot Learning (FSL) is a challenging task, \emph{i.e.}, how to recognize novel classes with few examples? Pre-training based methods effectively tackle the problem by pre-train…
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
Yuwen Du, Rui Ye, Shuo Tang +4
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The t…
Data Quality Control in Federated Instruction-tuning of Large Language Models
Yaxin Du, Rui Ye, Fengting Yuchi +4
Federated Learning (FL) enables privacy-preserving collaborative instruction tuning of large language models (LLMs) by leveraging massively distributed data. However, the decentral…
Learning behavior accounts for background-related advantage in AI-assisted education
Jingwei Yi, Yueqi Xie, Jiyan He +7
Generative AI has been found, and will likely be found increasingly, useful in education. However, existing AI-for-education studies provide inconsistent evidence on its average ef…
Tongyi DeepResearch Technical Report
Tongyi DeepResearch Team, Baixuan Li, Bo Zhang +54
We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking research tasks. To incentivize autonomous…
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
Litu Ou, Kuan Li, Huifeng Yin +8
Confidence in LLMs is a useful indicator of model uncertainty and answer reliability. Existing work mainly focused on single-turn scenarios, while research on confidence in complex…
FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
Rui Ye, Rui Ge, Xinyu Zhu +5
Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM). Following this training paradigm, the c…
Toward Efficient Agents: Memory, Tool learning, and Planning
Xiaofang Yang, Lijun Li, Heng Zhou +12
Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, whi…
Construction of various time-dependent Hamiltonians on a single photonic chip
Rui Ye, Guangzhen Li, Shuai Wan +12
Integrated photonics provides an important platform for simulating physical models with high-performance chip-scale devices, where the lattice size and the time-dependence of a mod…
FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units
Shaoheng Fang, Rui Ye, Wenhao Wang +5
Roadside unit (RSU) can significantly improve the safety and robustness of autonomous vehicles through Vehicle-to-Everything (V2X) communication. Currently, the usage of a single R…
Nonreciprocal interactions in crowd dynamics: investigating the impact of moving threats on pedestrian speed preferences
Shaocong Xie, Rui Ye, Xiaolian Li +8
Nonreciprocal interaction crowd systems, such as human-human, human-vehicle, and human-robot systems, often have serious impacts on pedestrian safety and social order. A more compr…
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
Rui Ye, Shuo Tang, Rui Ge +4
LLM-based multi-agent systems (MAS) have shown significant potential in tackling diverse tasks. However, to design effective MAS, existing approaches heavily rely on manual configu…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Yijun Lu, Rui Ye, Jiajun Wang +4
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for…
Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation
Shuo Tang, Xianghe Pang, Zexi Liu +6
Post-training is essential for enabling large language models (LLMs) to follow human instructions. However, its effectiveness depends on high-quality instruction data, which is cha…
MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users
Wenhao Wang, Mengying Yuan, Zijie Yu +5
The advancement of mobile GUI agents has opened new opportunities for automating tasks on mobile devices. Training these agents requires large-scale high-quality data, which is pro…
Incentivizing Inclusive Contributions in Model Sharing Markets
Enpei Zhang, Jingyi Chai, Rui Ye +2
While data plays a crucial role in training contemporary AI models, it is acknowledged that valuable public data will be exhausted in a few years, directing the world's attention t…
Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning
Shuo Tang, Rui Ye, Chenxin Xu +3
Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server, with each agent solving varied…
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Zhaopeng Feng, Liangcai Su, Zhen Zhang +16
As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing cont…
BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent Pair
Xianghe Pang, Shuo Tang, Rui Ye +3
Effective information seeking in the vast and ever-growing digital landscape requires balancing expansive search with strategic reasoning. Current large language model (LLM)-based…
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
Yijun Lu, Rui Ye, Yuwen Du +3
Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can over…
Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale
Linfeng Zhang, Siheng Chen, Yuzhu Cai +46
AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assi…
AgentFold: Long-Horizon Web Agents with Proactive Context Management
Rui Ye, Zhongwang Zhang, Kuan Li +12
LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Preva…
MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning
Baoquan Zhang, Hao Jiang, Xutao Li +3
Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with few examples. Recently, lots of methods have been proposed from the perspective of meta-le…
Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Xinyu Zhu, Yuzhu Cai, Zexi Liu +8
The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic cohere…
Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
Xianghe Pang, Shuo Tang, Rui Ye +4
Aligning large language models (LLMs) with human values is imperative to mitigate potential adverse effects resulting from their misuse. Drawing from the sociological insight that…
Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
Zhenyang Ni, Rui Ye, Yuxi Wei +3
Vision-Large-Language-models(VLMs) have great application prospects in autonomous driving. Despite the ability of VLMs to comprehend and make decisions in complex scenarios, their…
Commissioning of te China-ADS injector-I testing facility
Fang Yan, Huiping Geng, Cai Meng +58
The 10 MeV accelerator-driven subcritical system (ADS) Injector-I test stand at Institute of High Energy Physics (IHEP) is a testing facility dedicated to demonstrate one of the tw…
OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
Rui Ye, Wenhao Wang, Jingyi Chai +6
Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields. While more data contributes to better performan…
High-performance thin-film lithium niobate Mach-Zehnder modulator on thick silica buffering layer
Xiaotian Xue, Yingdong Xu, Wenjun Ding +9
High-speed photonic integrated circuits leveraging the thin-film lithium niobate (TFLN) platform present a promising approach to address the burgeoning global data traffic demands.…
Federated Learning Empowered by Generative Content
Rui Ye, Xinyu Zhu, Jingyi Chai +2
Federated learning (FL) enables leveraging distributed private data for model training in a privacy-preserving way. However, data heterogeneity significantly limits the performance…
EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale
Xinyu Zhu, Yuzhu Cai, Zexi Liu +20
The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing…
CT Radiomics-Based Explainable Machine Learning Model for Accurate Differentiation of Malignant and Benign Endometrial Tumors: A Two-Center Study
Tingrui Zhang, Honglin Wu, Zekun Jiang +9
Aimed to develop and validate a CT radiomics-based explainable machine learning model for precise diagnosing malignancy and benignity specifically in endometrial cancer (EC) patien…
FedDisco: Federated Learning with Discrepancy-Aware Collaboration
Rui Ye, Mingkai Xu, Jianyu Wang +3
This work considers the category distribution heterogeneity in federated learning. This issue is due to biased labeling preferences at multiple clients and is a typical setting of…
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
Zexi Liu, Jingyi Chai, Xinyu Zhu +5
The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-ba…
FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data
Wenhao Wang, Zijie Yu, Rui Ye +3
Mobile agents have attracted tremendous research participation recently. Traditional approaches to mobile agent training rely on centralized data collection, leading to high cost a…
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
Yuwen Du, Rui Ye, Shuo Tang +4
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains domin…
ConfusionPrompt: Practical Private Inference for Online Large Language Models
Peihua Mai, Youjia Yang, Ran Yan +2
State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant priv…
RAP-Net: Region Attention Predictive Network for Precipitation Nowcasting
Chuyao Luo, ZhengZhang, Rui Ye +2
Natural disasters caused by heavy rainfall often cost huge loss of life and property. To avoid it, the task of precipitation nowcasting is imminent. To solve the problem, increasin…
Investigating the effect of expected travel distance on individual descent speed in the stairwell with super long distance
Xingpeng Xu, Zhiming Fang, Rui Ye +2
Currently, there is an increasing number of super high-rise buildings in urban cities, the issue of evacuation in emergencies from such buildings comes to the fore. An evacuation e…
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
Kuan Li, Zhongwang Zhang, Huifeng Yin +14
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on…
Observation of non-Hermitian antichiral edge currents
Rui Ye, Yanyan He, Guangzhen Li +8
Non-Hermitian topological photonics is of great interest in bridging topological matter with gain/dissipation engineering in optics. A key problem in this direction is the interpla…
SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification
Baoquan Zhang, Shanshan Feng, Xutao Li +2
Few-Shot Remote Sensing Scene Classification (FSRSSC) is an important task, which aims to recognize novel scene classes with few examples. Recently, several studies attempt to addr…
PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
Tingjia Miao, Jiawen Dai, Jingkun Liu +18
Advances in LLMs have produced agents with knowledge and operational capabilities comparable to human scientists, suggesting potential to assist, accelerate, and automate research.…