BZPEER
More

Discover

About BZPEERSearchGraph

Research tools

HomeCollectionsResearchCollaborationPublish

Network

ExpertsCommunities

Opportunities

Listings

Account

Log inCreate account
Log inCreate account

Graph explorer

Research map

Explore the papers, people and topics connected to your research.

Hanlin Tang
SearchCollections
Map detail
Hanlin Tang23 visible / 23 total nodes / 79 links

Drag to move · Scroll or pinch to zoom · Select a node for details

Co-authorshipRelated contextCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipCo-authorshipWorks onWorks onAuthorshipAuthorshipAuthorshipAuthorshipWorks onWorks onAuthorshipWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onWorks onAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipTopic signalTopic signalTopic signalTopic signalAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipHanlin TangAHanlin TangResearcherFull Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training StepsWFull Attention Strikes ...preprint / 2026Lan TaoALan TaoResearcherYanke ZhouAYanke ZhouResearcherYiduo LiAYiduo LiResearcherMaohua LiAMaohua LiResearcherKan LiuAKan LiuResearcherLin QuALin QuResearcherYuan YaoAYuan YaoResearcherXiaoxing MaAXiaoxing MaResearcherMKQ-BERT: Quantized BERT with 4-bits Weights and ActivationsWMKQ-BERT: Quantized BER...preprint / 2022APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD AlgorithmWAPMSqueeze: A Communica...preprint / 2020DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated CompressionWDoubleSqueeze: Parallel...preprint / 2020A role for recurrent processing in object completion: neurophysiological, psychophysical and computational"evidenceWA role for recurrent pr...preprint / 2014Computation and LanguageTComputation and Language14115 worksArtificial IntelligenceTArtificial Intelligence22915 worksCentral Server Free Federated Learning over Single-sided Trust Social NetworksWCentral Server Free Fed...preprint / 2020Mimic The Raw Domain: Accelerating Action Recognition in the Compressed DomainWMimic The Raw Domain: A...preprint / 2020Emergence of Separable Manifolds in Deep Language RepresentationsWEmergence of Separable ...preprint / 2020Untangling in Invariant Speech RecognitionWUntangling in Invariant...preprint / 2020Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural NetworksWShifted and Squeezed 8-...preprint / 2020MLPerf Training BenchmarkWMLPerf Training Benchmarkpreprint / 2020SpaceNet MVOI: a Multi-View Overhead Imagery DatasetWSpaceNet MVOI: a Multi-...preprint / 2019
Person22 links

Hanlin Tang

Researcher

PaperFull Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training StepsAuthorship / preprint / 2026PersonLan TaoCo-authorship / ResearcherPersonYanke ZhouCo-authorship / ResearcherPersonYiduo LiCo-authorship / ResearcherPersonMaohua LiCo-authorship / ResearcherPersonKan LiuCo-authorship / ResearcherPersonLin QuCo-authorship / ResearcherPersonYuan YaoCo-authorship / Researcher

Personal maps

Sign in to save graph views

Saved views keep the query, focus and filters attached so you can return to the same research slice later.

Sign in

Public snapshots

1 shared view(s)