Amine Benhalloum
@amine_benh
Followers
215
Following
1K
Media
0
Statuses
138
Agents @Meta Superintelligence Labs
Joined December 2013
We released ARE and Gaia2 one week ago, time to share some observations and add new models to the leaderboard! https://t.co/BiiRGyfdXa
huggingface.co
0
7
22
(🧵) Today, we release Meta Code World Model (CWM), a 32-billion-parameter dense LLM that enables novel research on improving code generation through agentic reasoning and planning with world models. https://t.co/BJSUCh2vtg
60
313
2K
🧠Great research from @Meta Superintelligence Labs. Proposes Meta Agents Research Environments (ARE) for scaling up agent environments and evaluations. ARE lets researchers build realistic agent environments, run agents asynchronously, and verify them cleanly. On top of it
2
11
27
Did you see that the Agent Research Environment is MCP compatible? -> using any MCP tools with any agent is now completely trivial! Check it out! We've used an LLM agent to 1) move a robot arm remotely 2) depending on real time web search results! :D How to in thread ^^
Wanna upgrade your agent game? With @AIatMeta , we're releasing 2 incredibly cool artefacts: - GAIA 2: assistant evaluation with a twist (new: adaptability, robustness to failure & time sensitivity) - ARE, an agent research environment to empower all! https://t.co/XzCuG8A2b8
1
8
31
Very cool work from Meta Superintelligence Lab. They are open-sourcing Meta Agents Research Environments (ARE), the platform they use to create and scale agent environments. Great resource to stress-test agents in environments closer to real apps. Read on for more:
39
183
1K
Our contribution to the second half of AI 🚀 This has been a joy to build.
🏗️ ARE: scaling up agent environments and evaluations In the LLM+RL era, evals and envs are the bottleneck Happy to release Gaia2, an extensible benchmark for agents aiming to reduce the sim2real gap + ARE, the platform in which Gaia2 is built Enjoy evaluating your agents! 👇
0
1
1
What did it take to beat our production Engine ? A story of model composition written by our engineering manager @loic_le_bel available on @medium! → https://t.co/iB2cNMoodO
#MachineLearning #AI
link.medium.com
We rolled out “DRACuLA” to bring more than 3% LT RexT uplift on adaptive conversion!
1
15
20
Merry Xmas🎄 from the @CriteoAILab Reco team to all #recsys practitioners. Read this ⬇️, then go checkout DeepR on GitHub, then plz send feedback ! 🙏 Share and enjoy ...
medium.com
Learn how we build complex pipelines using Hadoop, Yarn, and MlFlow.
0
4
21
💰GIVEAWAY: @FrontendMasters have been very generous and have 5 prepaid codes to share that will give you 6 months FREE learning. I'll select 5 random retweeters of this tweet in 24 hours time. ⚡️RT to enter!⚡️ *you'll be contacted via DM with a special link to claim
12
626
190
We are hiring a senior software engineer in our recommendation team in Paris @CriteoEng Fancy distributed systems and machine learning? =>
0
8
7
On Wednesday, the 10th of june 2020, the 28th #DataScience #Leuven #Meetup will be a digital edition once again, with speakers @fishnets88 (RASA), @amine_benh (Criteo) and Sam Vandormael (Altares). More info: https://t.co/S8rvvQr2vV
0
7
6
Have you been drowning in BERT papers? We have. So... the first ever... Primer in BERTology is out! https://t.co/FoUK9fw6SM We survey over 40 papers on BERT's linguistic knowledge, compression, architecture tweaks, multilinguality, and more! With OlgaKovaleva & @arumshisky.
arxiv.org
Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150...
5
295
973
Awesome !
My student Denis wrote a formal semantics for the French tax code, complete with Coq proof of soundness and SMT queries to uncover unfair tax hikes. PL for fiscal justice!
0
0
0
We took a day to fight against covariate shift and optimizer's curse during the Crash Course on Modern recommendation for real world practitioners with @flavianv @amine_benh @Martinbpr @ihtiihti & David Rohde. Thank you to all the participants! #AI #MachineLearning
0
9
18
Yesterday's #AI #recsys Modern Recommendation course was very exciting and thrilling ! I want to thank mainly (and lots of other ppl actually) @CriteoAILab @RecoGym David Rohde @flavianv @amine_benh @Martinbpr @ihtiihti
1
1
4
Great speakers today to present our Crash-course on Modern recommendation for real-world practitioners! Thanks to @flavianv @amine_benh @Martinbpr @ihtiihti & David Rohde.
2
10
27
Get ready for our next Crash-course dedicated to Modern recommendation for real-world practitioners! It will take place on December 6th. Call for application deadline is November 18th. #AI #MachineLearning. Apply here:
0
2
12
Get ready for our next Crash-course dedicated to Modern recommendation for real-world practitioners! It will take place on December 6th. Call for application deadline is November 18th. #AI #MachineLearning. Apply here:
3
12
40