BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Yuchen Shi

Yuchen Shi contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningArtificial IntelligenceApplicationsComputation and LanguageComputer VisionCryptography and SecurityDistributed, Parallel, and Cluster Computingeess.SPInformation Theorymath.ITMethodologyMultiagent SystemsSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
8works
0followers
13topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

8 published item(s)

preprint2026arXiv

Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention

Federated learning relies on effective client selection to alleviate the performance degradation caused by data heterogeneity. Most existing methods assume full visibility of all clients at each communication round. However, in large-scale or edge-based deployments, the server can only access a subset of clients due to communication, mobility, or availability constraints, resulting in partial visibility where only a subset of clients is observable for aggregation in each communication round. In this paper, we formulate federated client selection under partial visibility as a Partially Observable Markov Decision Process (POMDP) and propose a Spatial-Temporal attention-based reinforcement learning framework. By integrating historical global models and client identity embeddings, the proposed method captures both the temporal contexts of training and the persistent characteristics of clients. Experimental results across multiple datasets demonstrate that our approach achieves superior performance compared to existing baselines in heterogeneous and partially visible settings, validating its effectiveness in addressing the challenges of incomplete observations in practical federated learning systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inference

Federated Learning (FL) facilitates collaborative model training across decentralized clients while preserving data privacy by avoiding raw data exchange. Despite its potential, FL performance is often compromised by data heterogeneity across clients. To address this, Clustered Federated Learning (CFL) groups clients with similar data distributions to improve model performance, but constrained by intra-cluster heterogeneity. Conversely, Personalized Federated Learning (PFL) tailors models to individual clients, but usually neglects the underlying structural similarities among clients. In this work, we investigate a probabilistic mixture (PM) scenario, where each client's local data distribution is modeled as a convex combination of several shared inherent distributions. To effectively model this structure, we propose FedGMI, a framework that utilizes Variational Autoencoders (VAEs) as generative density estimators to represent these inherent distributions and infer the mixture components of clients' local data distributions. This approach enables structured personalization without sacrificing the benefits of collaborative learning. Extensive experiments demonstrate that FedGMI effectively characterizes and discriminate the inherent distributions, as well as accurately estimates mixture proportions. Furthermore, FedGMI maintains robust performance even under communication cost constraints.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing task verification is treated as a passive, post-hoc process: a verifier (i.e., rule-based scoring script, reward or critic model, and LLM-as-a-Judge) analyzes the agent's entire interaction trajectory to determine if the agent succeeds. Such processing of verbose context that contains irrelevant, noisy history poses challenges to the verification protocols and therefore leads to prohibitive cost and low reliability. To overcome this bottleneck, we propose SmartSnap, a paradigm shift from this passive, post-hoc verification to proactive, in-situ self-verification by the agent itself. We introduce the Self-Verifying Agent, a new type of agent designed with dual missions: to not only complete a task but also to prove its accomplishment with curated snapshot evidences. Guided by our proposed 3C Principles (Completeness, Conciseness, and Creativity), the agent leverages its accessibility to the online environment to perform self-verification on a minimal, decisive set of snapshots. Such evidences are provided as the sole materials for a general LLM-as-a-Judge verifier to determine their validity and relevance. Experiments on mobile tasks across model families and scales demonstrate that our SmartSnap paradigm allows training LLM-driven agents in a scalable manner, bringing performance gains up to 26.08% and 16.66% respectively to 8B and 30B models. The synergizing between solution finding and evidence seeking facilitates the cultivation of efficient, self-verifying agents with competitive performance against DeepSeek V3.1 and Qwen3-235B-A22B. Code is available at: https://github.com/TencentYoutuResearch/SmartSnap

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Existing Large Language Model (LLM) agent frameworks face two significant challenges: high configuration costs and static capabilities. Building a high-quality agent often requires extensive manual effort in tool integration and prompt engineering, while deployed agents struggle to adapt to dynamic environments without expensive fine-tuning. To address these issues, we propose \textbf{Youtu-Agent}, a modular framework designed for the automated generation and continuous evolution of LLM agents. Youtu-Agent features a structured configuration system that decouples execution environments, toolkits, and context management, enabling flexible reuse and automated synthesis. We introduce two generation paradigms: a \textbf{Workflow} mode for standard tasks and a \textbf{Meta-Agent} mode for complex, non-standard requirements, capable of automatically generating tool code, prompts, and configurations. Furthermore, Youtu-Agent establishes a hybrid policy optimization system: (1) an \textbf{Agent Practice} module that enables agents to accumulate experience and improve performance through in-context optimization without parameter updates; and (2) an \textbf{Agent RL} module that integrates with distributed training frameworks to enable scalable and stable reinforcement learning of any Youtu-Agents in an end-to-end, large-scale manner. Experiments demonstrate that Youtu-Agent achieves state-of-the-art performance on WebWalkerQA (71.47\%) and GAIA (72.8\%) using open-weight models. Our automated generation pipeline achieves over 81\% tool synthesis success rate, while the Practice module improves performance on AIME 2024/2025 by +2.7\% and +5.4\% respectively. Moreover, our Agent RL training achieves 40\% speedup with steady performance improvement on 7B LLMs, enhancing coding/reasoning and searching capabilities respectively up to 35\% and 21\% on Maths and general/multi-hop QA benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

FedNC: A Secure and Efficient Federated Learning Method with Network Coding

Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network information theory, and formulate an original FL communication framework, FedNC, which is inspired by Network Coding (NC). The main idea of FedNC is mixing the information of the local models by making random linear combinations of the original parameters, before uploading for further aggregation. Due to the benefits of the coding scheme, both theoretical and experimental analysis indicate that FedNC improves the performance of traditional FL in several important ways, including security, efficiency, and robustness. To the best of our knowledge, this is the first framework where NC is introduced in FL. As FL continues to evolve within practical network frameworks, more variants can be further designed based on FedNC.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Improving Information Cascade Modeling by Social Topology and Dual Role User Dependency

In the last decade, information diffusion (also known as information cascade) on social networks has been massively investigated due to its application values in many fields. In recent years, many sequential models including those models based on recurrent neural networks have been broadly employed to predict information cascade. However, the user dependencies in a cascade sequence captured by sequential models are generally unidirectional and inconsistent with diffusion trees. For example, the true trigger of a successor may be a non-immediate predecessor rather than the immediate predecessor in the sequence. To capture user dependencies more sufficiently which are crucial to precise cascade modeling, we propose a non-sequential information cascade model named as TAN-DRUD (Topology-aware Attention Networks with Dual Role User Dependency). TAN-DRUD obtains satisfactory performance on information cascade modeling through capturing the dual role user dependencies of information sender and receiver, which is inspired by the classic communication theory. Furthermore, TANDRUD incorporates social topology into two-level attention networks for enhanced information diffusion prediction. Our extensive experiments on three cascade datasets demonstrate that our model is not only superior to the state-of-the-art cascade models, but also capable of exploiting topology information and inferring diffusion trees.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Conditional Kernel Density Estimation Considering Autocorrelation for Renewable Energy Probabilistic Modeling

Renewable energy is essential for energy security and global warming mitigation. However, power generation from renewable energy sources is uncertain due to volatile weather conditions and complex equipment operations. To improve equipment's operation efficiency, it is important to understand and characterize the uncertainty in renewable power generation. In this paper, we proposed a conditional kernel density estimation method to model the distribution of equipment's power output given any weather conditions. It explicitly accounts for the temporal dependence in the data stream and uses an iterative procedure to reduce the bias in kernel density estimation. Compared with existing literature, our approach is especially useful for the purposes of equipment condition monitoring or short-term renewable energy forecasting, where the data dependence plays a more significant role. We demonstrate our method and compare it with alternatives through real applications.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Phase I analysis of hidden operating status for wind turbine

Data-driven methods based on Supervisory Control and Data Acquisition (SCADA) become a recent trend for wind turbine condition monitoring. However, SCADA data are known to be of low quality due to low sampling frequency and complex turbine working dynamics. In this work, we focus on the phase I analysis of SCADA data to better understand turbines' operating status. As one of the most important characterization, the power curve is used as a benchmark to represent normal performance. A powerful distribution-free control chart is applied after the power generation is adjusted by an accurate power curve model, which explicitly takes into account the known factors that can affect turbines' performance. Informative out-of-control segments have been revealed in real field case studies. This phase I analysis can help improve wind turbine's monitoring, reliability, and maintenance for a smarter wind energy system.

0 citations0 reviewsNo code linkedOpen access