Andrej Jovanović
@itsmaddox_j
Followers
158
Following
917
Media
6
Statuses
158
ML Research @CaMLSys. Interested in distributed and collaborative machine learning | Prev @ISTAustria & MLMI @Cambridge_Eng
Unknown
Joined October 2023
I had a lot of fun working with everyone at ISTA-DASLab to bring you Panza V2. On a personal note: it is scarily impressive how the model adapted to my email voice in just a few samples. This is the future of personalised LLMs: private and on-device! Check it out! 🚀.
Introducing Panza V2, our personalized LLM writing assistant, running entirely on-device! Now faster and easier to use: .* Local serving via GMail extension.* Cloud training via @LightningAI Studio.* More models, including @AIatMeta LLama-3.2.* Inference w/ @ollama!.Details:
2
1
12
RT @Cohere_Labs: Don't forget to join us tomorrow, July 3rd as we host @tonysilveti for a session on "Training neural networks at any scale….
0
5
0
An absolute privilege to be involved with all the fantastic individuals at the @Cohere_Labs community! This is your sign to join :D.
🌟This month we are spotlighting @itsmaddox_j, one of our leads for the ML Theory Program! Andrej works as a research assistant with CaMLSys group at the University of Cambridge and focuses on compression/efficiency within large-scale distributed (federated) optimisation.
0
2
17
RT @Cohere_Labs: Join our ML Theory group next week as they welcome @tonysilveti on July 3rd for a presentation on "Training neural network….
0
13
0
For those of you that missed my talk, and are interested in hearing about using federated learning for training LLMs, the talk is now online!. Link is below:.
Join me to hear about decentralised training, why it works and what opportunities it can unlock 🚀. Many thanks to @Sree_Harsha_N for the invitation!.
1
0
4
RT @simon_ycl: Introducing RL2: Ray-Less Reinforcement Learning for LLMs 🚀 . Want to run RL experiments but tired of complicated abstractio….
0
35
0
RT @CaMLSys: This week, we are delighted to host Max Ryabinin (@m_ryabinin) of @togethercompute who will be speaking at the Cambridge ML Sy….
0
2
0
RT @Cohere_Labs: Be sure to join our ML Efficiency Group tomorrow, June 17th as they host @itsmaddox_j for a session on "Communication-effi….
0
2
0
RT @niclane7: The future of open-source AI is decentralized — and it’s arriving in San Francisco this September.
0
2
0
Super excited to host @AmbroiseOdonnat next week, particularly to hear about the connection between LLMs and their n-gram predecessors!.
Our ML Theory group is looking forward to welcoming @AmbroiseOdonnat next week on Thursday, June 19th for a session on "Large Language Models as Markov Chains"
0
2
18
RT @Cohere_Labs: Our ML Efficiency Group is excited to welcome @itsmaddox_j on Tuesday, June 17th for an insightful presentation of "Commun….
0
3
0
Join me to hear about decentralised training, why it works and what opportunities it can unlock 🚀. Many thanks to @Sree_Harsha_N for the invitation!.
@itsmaddox_j will be presenting at the ML Efficiency group - this is going to be a very fun session :D Andrej is super passionate and I hope this will be useful for anyone who'd like to make sense of why decentralized training is exciting. Join us
2
8
23
Don't forget to join us today!.
We are super excited to host Frederik next Friday 🪇 Cannot wait to dig deep into why Adam is such a robust optimiser, and why it is the de facto standard for many applications. Do tune in! 📺.
0
0
5
We are super excited to host Frederik next Friday 🪇 Cannot wait to dig deep into why Adam is such a robust optimiser, and why it is the de facto standard for many applications. Do tune in! 📺.
Next Friday, May 23rd, our ML Theory group is excited to host Frederik Kunstner for a session on "Heavy-tailed imbalance and why Adam outperforms gradient descent on language models.". Special shoutout to @aniervs, @itsmaddox_j, and @ThangChu77 for organizing this event 🎉
0
0
4
RT @Cohere_Labs: Next Friday, May 23rd, our ML Theory group is excited to host Frederik Kunstner for a session on "Heavy-tailed imbalance a….
0
4
0
RT @CaMLSys: Photon: A New SOTA for Decentralized LLM pre-training at @MLSysConf 2025. Poster today; talk on Thursday. @lorenzosani97 conve….
0
6
0
RT @niclane7: We're hiring at @CaMLSys for engineering support to scale our decentralized AI research. Find me at @MLSysConf this week, or….
0
4
0
RT @Cohere_Labs: Thanks to all that attended our session with @jxbz last week, it was a great opportunity to come together and hear about "….
0
3
0
RT @Cohere_Labs: @jxbz 📽️ If you missed the talk, check out the full recording here: Special thank you to our spea….
0
6
0