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

Zengxiang Li

Zengxiang Li contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Cryptography and SecurityMachine LearningArtificial IntelligenceComputation and LanguageComputer VisionDistributed, Parallel, and Cluster Computingeess.SYHuman-Computer InteractionNetworking and Internet ArchitectureSystems and Control

Trust snapshot

Quick read

Trust 19 - UnverifiedVerification L1Unclaimed author
5works
0followers
10topics
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

5 published item(s)

preprint2026arXiv

MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models

Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising solution by optimizing policies using answer correctness signals. Despite their effectiveness, prevailing RLVR methods face two critical limitations. First, much of the sampling budget is wasted on trajectories doomed to fail due to early visual description errors. Second, sparse rewards cannot distinguish whether failures stem from visual perception or reasoning stages. We introduce MIRL, a decoupled framework that addresses both limitations by leveraging mutual information (MI) between generated descriptions and visual inputs as a cheap pre-screening signal. This enables intelligent budget allocation toward high-potential trajectories via forking, while decoupled training provides independent MI-based rewards for visual perception optimization, resolving reward blindness. Experiments on six vision-language reasoning benchmarks demonstrate that MIRL achieves 70.22% average accuracy and successfully surpasses the performance of sampling 16 complete trajectories using only 10 pre-samples with top-6 selection (25% fewer complete trajectories). Our code is available at: https://anonymous.4open.science/r/mirl-main/.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Data

Federated learning (FL) and split learning (SL) are the two popular distributed machine learning (ML) approaches that provide some data privacy protection mechanisms. In the time-series classification problem, many researchers typically use 1D convolutional neural networks (1DCNNs) based on the SL approach with a single client to reduce the computational overhead at the client-side while still preserving data privacy. Another method, recurrent neural network (RNN), is utilized on sequentially partitioned data where segments of multiple-segment sequential data are distributed across various clients. However, to the best of our knowledge, it is still not much work done in SL with long short-term memory (LSTM) network, even the LSTM network is practically effective in processing time-series data. In this work, we propose a new approach, LSTMSPLIT, that uses SL architecture with an LSTM network to classify time-series data with multiple clients. The differential privacy (DP) is applied to solve the data privacy leakage. The proposed method, LSTMSPLIT, has achieved better or reasonable accuracy compared to the Split-1DCNN method using the electrocardiogram dataset and the human activity recognition dataset. Furthermore, the proposed method, LSTMSPLIT, can also achieve good accuracy after applying differential privacy to preserve the user privacy of the cut layer of the LSTMSPLIT.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a smart home system. To help manufacturers develop a smart home system, we design a federated learning (FL) system leveraging the reputation mechanism to assist home appliance manufacturers to train a machine learning model based on customers' data. Then, manufacturers can predict customers' requirements and consumption behaviors in the future. The working flow of the system includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL system. Since records on the blockchain are untampered, malicious customers or manufacturers' activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers' privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Privacy-preserving Weighted Federated Learning within Oracle-Aided MPC Framework

This paper studies privacy-preserving weighted federated learning within the oracle-aided multi-party computation (MPC) framework. The contribution of this paper mainly comprises the following three-fold: In the first fold, a new notion which we call weighted federated learning (wFL) is introduced and formalized inspired by McMahan et al.'s seminal paper. The weighted federated learning concept formalized in this paper differs from that presented in McMahan et al.'s paper since both addition and multiplication operations are executed over ciphers in our model while these operations are executed over plaintexts in McMahan et al.'s model. In the second fold, an oracle-aided MPC solution for computing weighted federated learning is formalized by decoupling the security of federated learning systems from that of underlying multi-party computations. Our decoupling formulation may benefit machine learning developers to select their best security practices from the state-of-the-art security tool sets; In the third fold, a concrete solution to the weighted federated learning problem is presented and analysed. The security of our implementation is guaranteed by the security composition theorem assuming that the underlying multiplication algorithm is secure against honest-but-curious adversaries.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning

Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where data is collected from end-users or IoT devices, so that it can discover insights behind real-world data, may not be feasible for many data-driven industry applications in light of such regulations. A new machine learning method, coined by Google as Federated Learning (FL) enables multiple participants to train a machine learning model collectively without directly exchanging data. However, recent studies have shown that there is still a possibility to exploit the shared models to extract personal or confidential data. In this paper, we propose to adopt Multi Party Computation (MPC) to achieve privacy-preserving model aggregation for FL. The MPC-enabled model aggregation in a peer-to-peer manner incurs high communication overhead with low scalability. To address this problem, the authors proposed to develop a two-phase mechanism by 1) electing a small committee and 2) providing MPC-enabled model aggregation service to a larger number of participants through the committee. The MPC enabled FL framework has been integrated in an IoT platform for smart manufacturing. It enables a set of companies to train high quality models collectively by leveraging their complementary data-sets on their own premises, without compromising privacy, model accuracy vis-a-vis traditional machine learning methods and execution efficiency in terms of communication cost and execution time.

0 citations0 reviewsNo code linkedOpen access