Scholar
Alexander Long
Google Scholar ID: msw1XCIAAAAJ
Pluralis Research
Decentralized Training
Protocol Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
213
H-index
4
i10-index
3
Publications
15
Co-authors
11
list available
Contact
No contact links provided.
Publications
10 items
Agora: Collective and Permissionless Internet-Scale Pretraining of Large Language Models
2026
Cited
0
Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo
2026
Cited
0
Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training
2026
Cited
0
Taming Curvature: Architecture Warm-Up for Stable Transformer Training
2026
Cited
0
Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
2026
Cited
0
SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training
2026
Cited
0
NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training
2026
Cited
0
AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism
2026
Cited
0
Load more
Resume (English only)
Co-authors
11 total
Thalaiyasingam Ajanthan
Pluralis Research | Australian National University
Co-author 2
Anton van den Hengel
Director of the Centre for Augmented Reasoning at AIML, and CommBank AI Scholar
Ravi Garg
University of Adelaide
Pulak Purkait
Amazon
Vu Nguyen
Senior ML Scientist, Amazon
Chunhua Shen
Zhejiang University
Gil Avraham
Pluralis Research
