Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Gensyn

Team
company
Verified
https://gensyn.ai
gensynai
gensyn-ai
Activity Feed

AI & ML interests

We network together the core resource for machine intelligence to flourish alongside human intelligence https://www.gensyn.ai/research

Recent Activity

oguzer  authored a paper 1 day ago
Training-Free Dynamic Upcycling of Expert Language Models
Erosinho  authored a paper 1 day ago
Training-Free Dynamic Upcycling of Expert Language Models
oguzer  authored a paper 1 day ago
Backdoor Attacks on Decentralised Post-Training
View all activity

Papers

Training-Free Dynamic Upcycling of Expert Language Models

Backdoor Attacks on Decentralised Post-Training

View all Papers

Ben's profile pictureGabriel P Andrade's profile pictureH's profile picturejohn donaghy's profile pictureSteve Glasper's profile pictureJeffrey Amico's profile picturePatrick's profile pictureDiogo Ortega's profile pictureMatt's profile pictureViktor Kolobarić's profile pictureAdam St Arnaud's profile pictureNikolay Blagoev's profile pictureOguzhan Ersoy's profile pictureBrian W's profile pictureShikhar Rastogi's profile pictureAlex's profile pictureGabrielle Vasquez's profile pictureMohammed Affan's profile pictureJesse Walker's profile picturet forbus's profile pictureFrank Wan's profile pictureDerek's profile pictureArasu Arun's profile pictureChristopher Nies's profile pictureSemih Kara's profile pictureEdward Phillip Flores Nuño's profile pictureJudson Bonneville's profile pictureEros Fanì's profile pictureEamonn Nugent's profile pictureYannis Stamelakos's profile pictureJordan Greenberg's profile picturejake peterson's profile pictureFrancis's profile picture
Gensyn 's Papers 9
10

Training-Free Dynamic Upcycling of Expert Language Models

Gensyn Gensyn
4
Submitted by
Oguzhan Ersoy
10

Backdoor Attacks on Decentralised Post-Training

Gensyn Gensyn
2
Submitted by
Oguzhan Ersoy
29

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Gensyn Gensyn
4
Submitted by
Ben
665

Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing

Gensyn Gensyn
1.69k 56
Submitted by
Ben
40

All is Not Lost: LLM Recovery without Checkpoints

Gensyn Gensyn
16 3
Submitted by
Ben
9

NoLoCo: No-all-reduce Low Communication Training Method for Large Models

Gensyn Gensyn
30 2
6

SkipPipe: Partial and Reordered Pipelining Framework for Training LLMs in Heterogeneous Networks

Gensyn Gensyn
48
9

Verde: Verification via Refereed Delegation for Machine Learning Programs

Gensyn Gensyn
19
5

HDEE: Heterogeneous Domain Expert Ensemble

Gensyn Gensyn
33
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs