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.

Mingyi Hong
SearchCollections
Map detail
Mingyi Hong26 visible / 26 total nodes / 73 links

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

Co-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 onWorks onWorks onWorks onWorks onAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipWorks onAuthorshipAuthorshipWorks onAuthorshipWorks onWorks onWorks onWorks onWorks onAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipAuthorshipTopic signalTopic signalTopic signalTopic signalTopic signalAuthorshipAuthorshipAuthorshipMingyi HongAMingyi HongResearcherRethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVRWRethinking Muon Beyond ...preprint / 2026Revisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning RatesWRevisiting the Adam-SGD...preprint / 2026CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMsWCUDAHercules: Benchmark...preprint / 2026Chongyu FanAChongyu FanResearcherGaowen LiuAGaowen LiuResearcherRamana Rao KompellaARamana Rao KompellaResearcherSijia LiuASijia LiuResearcherAthanasios GlentisAAthanasios GlentisResearcherDawei LiADawei LiResearcherChung-Yiu YauAChung-Yiu YauResearcherShiyang LiAShiyang LiResearcherZijian ZhangAZijian ZhangResearcherGuangyan SunAGuangyan SunResearcherYuebo LuoAYuebo LuoResearcherWinson ChenAWinson ChenResearcherMachine LearningTMachine Learning49008 worksA Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-CriticWA Two-Timescale Framewo...preprint / 2022On the Divergence of Decentralized Non-Convex OptimizationWOn the Divergence of De...preprint / 2020Lower Bounds Optimization for Coordinated Linear Transmission Beamformer Design in Multicell Network DownlinkWLower Bounds Optimizati...preprint / 2011Distributed Uplink Resource Allocation in Cognitive Radio Networks -- Part I: Equilibria and Algorithms for Power AllocationWDistributed Uplink Reso...preprint / 2011Distributed Uplink Resource Allocation in Cognitive Radio Networks -- Part II: Equilibria and Algorithms for Joint Access Point Selection and Power AllocationWDistributed Uplink Reso...preprint / 2011On the Linear Convergence of the Alternating Direction Method of MultipliersWOn the Linear Convergen...preprint / 2013Mechanism Design for Base Station Association and Resource Allocation in Downlink OFDMA NetworkWMechanism Design for Ba...preprint / 2012Signal Processing and Optimal Resource Allocation for the Interference ChannelWSignal Processing and O...preprint / 2012Joint User Grouping and Linear Virtual Beamforming: Complexity, Algorithms and Approximation BoundsWJoint User Grouping and...preprint / 2013
Person25 links

Mingyi Hong

Researcher

PaperRethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVRAuthorship / preprint / 2026PaperRevisiting the Adam-SGD Gap in LLM Pre-Training: The Role of Large Effective Learning RatesAuthorship / preprint / 2026PaperCUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMsAuthorship / preprint / 2026PersonChongyu FanCo-authorship / ResearcherPersonGaowen LiuCo-authorship / ResearcherPersonRamana Rao KompellaCo-authorship / ResearcherPersonSijia LiuCo-authorship / ResearcherPersonAthanasios GlentisCo-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)