Eros Fanì (@ErosFani) profile picture

ML Researcher @ Gensyn Building scalable, distributed models over uniquely decentralised and heterogeneous infrastructure

Joined September 2021
Eros Fanì retweeted
I'm excited that our paper with @ErosFani, “Training-Free Dynamic Upcycling of Expert Language Models,” has been accepted to NeurIPS 2026! 🎉 We introduce DUME: a way to combine already-trained domain experts into one Mixture-of-Experts model without post-merge training. 🧵
1
7
2
14
4,124
Eros Fanì retweeted
“With IR3DE-AXL, we built a collective inference network prototype where participants can contribute expert models, use models served by others, or do both” @oguzer90 explains the how using AXL with IR3DE combines p2p networking and local expert routing gensyn.ai/research/ir3de-axl…
Inference does not have to look like one centralised gateway routing every prompt to a fixed model catalogue. With IR3DE-AXL, we built a collective inference network prototype where participants can contribute expert models, use models served by others, or do both. gensyn.ai/research/ir3de-axl… 🧵1/6
4
10
32
7,347
Eros Fanì retweeted
Look beyond one-size-fits-all LLMs with IR3DE New research published by Gensyn's @ErosFani and @oguzer90 Read the blog post linked below and follow through to the published paper on @arxiv
Look beyond one-size-fits-all LLMs with IR3DE Introducing IR3DE: a router that selects the best expert LLM for any prompt. No complex neural network or gradient-based training—just linear algebra and a linear layer achieving 98.4% in reasoning settings blog.gensyn.ai/look-beyond-o…
14
12
1
54
12,641
Look beyond one-size-fits-all LLMs with IR3DE Introducing IR3DE: a router that selects the best expert LLM for any prompt. No complex neural network or gradient-based training—just linear algebra and a linear layer achieving 98.4% in reasoning settings blog.gensyn.ai/look-beyond-o…
3
4
1
14
10,489
Most expert routers need a full language model plus all your domain data pooled in one place to train. IR3DE skips both. Domain stats are computed separately and then summed—ideal for privacy-constrained, decentralized settings.
1
1
1
182
Bonus: you can add or remove expert models without retraining the router from scratch. Cheap, fast, and adaptable—useful as the list of available LLMs keeps growing.
1
1
1
152
Eros Fanì retweeted
At 11am ET join us as @ErosFani and @oguzer90 talk through the recently released research paper: IR3DE: A Linear Router for Large Language Models xitter.cf/i/spaces/1mxPaaBdLNgKN

5
4
30
2,292
Eros Fanì retweeted
Join @ErosFani tomorrow as he talk through the recent paper on DUME - Dynamic Upcycling of Mixture-of-Experts. xitter.cf/i/spaces/1nxnRYlmyNYxO…

11
6
1
63
12,854
Eros Fanì retweeted
Gensyn team members are in attendance at two major conferences today - the International Conference on Learning Representations in Rio and EuroMLSys in Edinburgh Find @oguzer90 and @ErosFani with papers at @iclr_conf and Nikolay Blagoev at @euromlsys Details below👇
14
11
1
143
12,404
Eros Fanì retweeted
A reminder for those attending @iclr_conf on April 27, Gensyn team members will be on site with two papers being presented. "Training-Free Dynamic Upcycling of Expert Language Models" "Backdoor Attacks on Decentralised Post-Training" Find details below and join them for more.
ICLR 2026, Rio de Janeiro, Apr 27 - Two Gensyn papers will be presented at @iclr_conf: "Training-Free Dynamic Upcycling of Expert Language Models" "Backdoor Attacks on Decentralised Post-Training" Gensyn team members will be there and workshop details can be found below👇
7
13
1
100
15,926
Eros Fanì retweeted
Replying to @ErosFani
@ErosFani and I are at ICLR’26. If you’re here and interested in decentralised AI, let’s meet!
ICLR 2026, Rio de Janeiro, Apr 27 - Two Gensyn papers will be presented at @iclr_conf: "Training-Free Dynamic Upcycling of Expert Language Models" "Backdoor Attacks on Decentralised Post-Training" Gensyn team members will be there and workshop details can be found below👇
6
17
798
Eros Fanì retweeted
ICLR 2026, Rio de Janeiro, Apr 27 - Two Gensyn papers will be presented at @iclr_conf: "Training-Free Dynamic Upcycling of Expert Language Models" "Backdoor Attacks on Decentralised Post-Training" Gensyn team members will be there and workshop details can be found below👇
11
10
6
103
32,050
Eros Fanì retweeted
"DUME provides a clean way to combine dense experts into a multidomain MoE – no compromises." Newly published research by Gensyn's @ErosFani, introducing a training-free way to turn multiple domain experts into a single multi domain model. blog.gensyn.ai/dume/
11
12
2
105
5,452
2/ Today's problems: - Separate expert models, embedding: heavy memory + slow inference - Model merging = destructive interference - Multitask training = complex, expensive, unstable DUME provides a clean way to combine dense experts into a multidomain MoE – no compromises.
1
7
503
3/ Even better, DUME allows you to dynamically add experts in new domains or remove existing ones without retraining, and it works naturally in decentralized and privacy-sensitive settings, scaling intelligence in a modular, efficient, and composable way.
7
338
Gensyn research team at NeurIPS! If you're excited about decentralised AI, verification, robustness, game theory, and more — come say hi! We’d love to meet you. Check out our events below 👇
The Gensyn team will be at NeurIPS next week, cohosting a series of community events with @akashnet and @PluralisHQ. If you’re in town, join us for co-working, discussion, and connection. Our research team will be on-site to share our latest thinking and progress in decentralized AI.
19
20
5
142
13,970