BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Qinnan Zhang

Qinnan Zhang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
eess.IVphysics.opticsArtificial IntelligenceComputation and LanguageComputer VisionDistributed, Parallel, and Cluster ComputingMachine Learning

Catalog footprint

What is connected

4works
7topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

Published work

4 published item(s)

preprint2026arXiv

FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models

Private data holds promise for improving LLMs due to its high quality, but its scattered distribution across data silos and the high computational demands of LLMs limit their deployment in federated environments. To address this, the transformer-based federated split models are proposed, which offload most model parameters to the server (or distributed clients) while retaining only a small portion on the client to ensure data privacy. Despite this design, they still face three challenges: 1) Peer-to-peer key encryption struggles to secure transmitted vectors effectively; 2) The auto-regressive nature of LLMs means that federated split learning can only train and infer sequentially, causing high communication overhead; 3) Fixed partition points lack adaptability to downstream tasks. In this paper, we introduce FedSEA-LLaMA, a Secure, Efficient, and Adaptive Federated splitting framework based on LLaMA2. First, we inject Gaussian noise into forward-pass hidden states to enable secure end-to-end vector transmission. Second, we employ attention-mask compression and KV cache collaboration to reduce communication costs, accelerating training and inference. Third, we allow users to dynamically adjust the partition points for input/output blocks based on specific task requirements. Experiments on natural language understanding, summarization, and conversational QA tasks show that FedSEA-LLaMA maintains performance comparable to centralized LLaMA2 and achieves up to 8x speedups in training and inference. Further analysis of privacy attacks and different partition points also demonstrates the effectiveness of FedSEA-LLaMA in security and adaptability.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning

Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but directly sharing them poses privacy risks. A common defense involves per-example $\ell_2$ clipping before prototype computation to bound sensitivity, followed by isotropic Gaussian noise to enforce Local Differential Privacy (LDP). However, Isotropic Gaussian Prototype Perturbation (IGPP) typically over-perturbs discriminative dimensions and struggles to balance the clipping threshold with representation fidelity. In this paper, we propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFLs. Motivated by the observation that dimension-wise class variance reflects discriminability, we introduce Variance-adaptive Prototype Perturbation (VPP), which allocates less noise to discriminative subspaces, preserving semantic separability while ensuring privacy. We further develop Distillation-guided Clipping Regularization (DCR), which enables feature norms to adaptively concentrate near the predefined clipping threshold while maintaining prediction consistency. Theoretical analysis shows that our groupwise mechanism provides privacy guarantees no weaker than the isotropic baseline under the same privacy constraints. Extensive experiments on multi-domain benchmarks demonstrate that VPDR achieves a superior privacy-utility trade-off, outperforming IGPP in personalized federated fine-tuning without sacrificing robustness against realistic attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Phase Shifter for Quantitative Phase Imaging

A single intensity-only holographic interferogram can records the full amplitude and phase information of optical field. However, current digital holography technologies cannot recover the lossless phase information from a single interferogram. In this paper, we provide an entirely new approach for the full-field quantitative phase imaging technology. We demonstrate that deep learning can be used to replace the entitative phase shifter, and quantitative phase imaging can obtain quantitative phase from a single interferogram in in-line holography. A deep-phase-shift network (DPS-net) is reported, which can be trained with simulation training data. The trained DPS-net can be used to generate multiple interferograms with arbitrary phase shift from a single interferogram as an artificial intelligence phase shifter. The ability and the accuracy of generating arbitrary phase shifts are verified, and the performance of the proposed method is also verified by the experimental interferogram. The results demonstrate that the proposed method can provide a full digital phase shifter with high-accuracy for the technology of dynamic quantitative phase measurement.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep-learning-based optical image hiding

A novel framework of optical image hiding based on deep learning (DL) is proposed in this paper, and hidden information can be reconstructed from an interferogram by using an end to end network with high-quality. By using the prior data between the hidden image and the object image, a generative adversarial network was trained so that it can learn the hiding model, which resulting in only an interferogram needs to be transmitted and recorded to reconstruct image. Moreover, reconstruction process can be obtained without the parameters in optical inverse diffraction and the reconstruction result will not be affected by the phase shifts deviation and noise, which is convenient for practical application. The feasibility and security of the proposed method are demonstrated by the optical experiment results.

0 citations0 reviewsNo code linkedOpen access