Maxence Faldor
@maxencefaldor
Followers
791
Following
575
Media
41
Statuses
145
PhD student @ImperialCollege. Research intern @SakanaAILabs.
Joined July 2021
The new @stateofaireport features our work OMNI-EPIC! 📰 https://t.co/FdeAhmGJHd We have recently released the code on GitHub, check it out: 💻 https://t.co/sNS7D2pZT7 🌟 https://t.co/plaaYwfe8A
🪩The @stateofaireport 2024 has landed! 🪩 Our seventh installment is our biggest and most comprehensive yet, covering everything you *need* to know about research, industry, safety and politics. As ever, here's my director’s cut (+ video tutorial!) 🧵
0
6
35
The narrative around LLMs is that they got better purely by scaling up pretraining *compute*. In reality, they got better by scaling up pretraining *data*, while compute is only a means to the end of cramming more data into the model. Data is the fundamental bottleneck. You can't
98
188
2K
We’re excited to introduce ShinkaEvolve: An open-source framework that evolves programs for scientific discovery with unprecedented sample-efficiency. Blog: https://t.co/Bj32AGXC3T Code: https://t.co/UMCSQaeOhd Like AlphaEvolve and its variants, our framework leverages LLMs to
27
238
1K
Almost exactly 10 years after joining @imperialcollege as a Postdoc, I am honoured to announce that I am now Professor in Machine Learning and Robotics! 👨🎓 🤖 My fantastic team found the best gift to celebrate this special occasion!
32
8
241
Harder, Better, Faster, Stronger, Real-time! We are excited to reveal Genie 3, our most capable real-time foundational world model. Fantastic cross-team effort led by @jparkerholder and @shlomifruchter. Below some interactive worlds and capabilities that were highlights for me
54
190
1K
Had a great time at #ICLR2025, especially at the Robot Learning Workshop, where our paper Instant Policy (w/ @Ed__Johns) won the Best Paper Award! It's an exciting time for in-context learning and robotics! 🦾 https://t.co/usWRrXNbTR
4
8
98
Several people from the AIRL lab and I are at ICLR'25 this week. Come to see our latest work and have a chat. See below for the full program!
1
9
36
We will be presenting OMNI-EPIC today afternoon at #ICLR2025 ! Do drop by to say hi, ask questions, or give any feedback 🤩👂 work done together with @maxencefaldor, @CULLYAntoine, @jeffclune
0
14
61
Thrilled that we have been recognized as a Top 100 AI startup! So proud of our team. ✨
We have been named among the top 100 Al startups globally by @CBinsights, alongside @Figure_robot, @wayve_ai and @dexoryHQ! With only a handful of gaming companies listed, we are proud to be defining a new category of interactive worlds and experiences https://t.co/tUeNPfzVZs
1
5
21
Excited to introduce Intelligent Go-Explore: Foundation model (FM) agents have the potential to be invaluable, but struggle to learn hard-exploration tasks! Our new algorithm drastically improves their exploration abilities via Go-Explore + FM intelligence. Led by @cong_ml🧵1/
1
7
60
I just arrived in Singapore for ICLR, where I will present: - OMNI-EPIC poster on Fri 25 Apr 15:00-17:30 - CAX poster on Sat 26 Apr 10:00-12:30 I am super happy that CAX got accepted at ICLR 2025 as an oral presentation. 🤩 If you are interested in open-endedness/artificial
Excited to release CAX v0.2.0! https://t.co/0T5i2CS2za Consider starring the GitHub repository to support the project! 🌟
4
11
78
The vision for CAX is to become the standard artificial life framework to support the next generation of discoveries in self-organization, emergence and open-ended evolution. Get started here:
colab.research.google.com
Run, share, and edit Python notebooks
0
1
8
Changes: - Better documentation and Getting Started Colab notebook 📚 - Fast hardware-accelerated rendering methods for all systems ⚡️ - Better metrics logging 📊 - Refactor existing complex systems such as Elementary CA, Life and Lenia to be more general and easier to use 🛠️
1
0
1
Excited to release CAX v0.2.0! https://t.co/0T5i2CS2za Consider starring the GitHub repository to support the project! 🌟
4
35
225
🚨 Schedule drop! 🚨 The World Models Workshop @ #ICLR2025 is coming🔥! Mark your calendars 🗓️ for April 28th 08:00-18:00.🕗 https://t.co/ZrHfrPCRsn We’re excited to welcome a fantastic lineup of speakers and panellists from across #Robotics, #RL, #GenerativeAI, and #Causality
1
17
118
Looking forward to representing the Open-Endedness research community with a keynote at @iclr_conf 2025 in Singapore! 🚀
Announcing the keynote speakers for #ICLR2025! Speakers will cover topics ranging from foundational advances in language models, AI safety, open-ended learning, and the nature of intelligence itself. https://t.co/nL73E3KtbG
3
15
158