
Nemotron @nvidia ex RL @poolsideai, @Huawei, @OfficialUoM @Manchester_NLP, @ecentua
Athens, Greece
Joined April 2012
- Tweets124
- Following570
- Followers406
- Likes647
Fenia Christopoulou retweeted
Today, we’re releasing Poolside Desktop Assistant.
One place to run coding agents across macOS, VS Code, and Visual Studio.
We built it for ourselves and have used it every day for the past year. Now we’re opening it up to everyone.
Our most capable model yet is out✨ An incredible achievement by a team of our size building models fully in-house!
Today we're releasing Laguna S 2.1, our most capable model to date.
It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes.
Capable enough to hold its own against models many times its size. Small enough to run on a single @NVIDIAAI DGX Spark.
Laguna S 2.1 is fully open under OpenMDW-1.1, with weights available today on @huggingface
poolside.ai/blog/introducing…
20
1,209
Fenia Christopoulou retweeted
Today we’re releasing Laguna XS 2.1.
It’s a small upgrade to the Laguna XS.2 model, the same 33B total / 3B active MoE and stronger results on multilingual coding and terminal-style tasks.
Available now on @huggingface, @OpenRouter, and via Poolside API.
Really cool internal tool built by @aalSonOfRavi that runs agents over trajectories to analyze them. In this case I set the goal to find any reward hacking on SWE Bench Pro by accessing GitHub.
Fenia Christopoulou retweeted
Looking forward to speaking at @aiDotEngineer next week together with @marah_i_abdin about synthetic data and pre-training at @poolsideai 🔥
I might show some base model evals of an upcoming models as well
Fenia Christopoulou retweeted
Today we’re releasing the weights for Laguna M.1,
our most capable model to date, with a 256K context length.
Both base and post-trained checkpoints are now available on Hugging Face under Apache 2.0.
Fenia Christopoulou retweeted
Laguna M.1 and XS.2 now support 256K context.
Laguna M.1 is now live with a 256K context window on the Poolside API and OpenRouter.
With this update, it reaches 45.8% on Terminal-Bench 2.0, improving long-horizon performance.
Laguna XS.2 is also moving to 256K today, with the updated config already available on Hugging Face.
Both models remain free to use.
Over 1T tokens have been processed since launch 4 weeks ago. Excited to see what people build with the longer context window.
Technical report is finally out 🚀
Today we’re publishing the technical report behind Laguna M.1 and Laguna XS.2.
This report opens up more of what went into them: Model Factory, pre-training data, distributed training, post-training, agent RL, quantization, and evaluation.
poolside.ai/assets/laguna/la…
Fenia Christopoulou retweeted
Poolside is hosting a 2-day model research hackathon in London.
Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intellect Lab.
Dates: May 29–30
Partners: @nvidia + @PrimeIntellect + @huggingface
Prize: NVIDIA DGX Spark
Agents need better models.
Better models need cracked researchers.
Link below.
We're releasing <𝙿𝚘𝚘𝚕𝙴𝚟𝚊𝚕.../> today, an open-source component for rendering eval charts. We built this to power the dozens of eval charts on poolside.ai, and now you can use it too. Accessible, beautiful, configurable, touch friendly and parseable at a glance.
Useful for model providers, harness developers and researchers alike.
pooleval.vercel.app
Fenia Christopoulou retweeted
Today we’re releasing Laguna M.1 and Laguna XS.2, our first public models.
Laguna XS.2 is our first open-weight release, with weights available today on Hugging Face:
huggingface.co/poolside/Lagu…
A few details on what went into them: large-scale pre-training, data mixture optimization, synthetic data, optimizer efficiency, and async agent RL.
Today we're launching our first public Poolside models: Laguna M.1 and Laguna XS.2, and we've built ❈Shimmer, an instant-on VM sandbox with Poolside Agent pre-installed so you can try them out.
Go play out our new models for free, and build something fun → shimmer.run
Beyond excited and proud to finally share what we have been building at @poolside!
✨Laguna XS.2 and M.1 are out! ✨
Today we’re releasing Laguna XS.2, Poolside’s first open-weight model.
It’s a 33B total / 3B active MoE model built for agentic coding and long-horizon tasks.
Trained fully in-house on our own stack. Runs on a single GPU. Released under Apache 2.0.
Links 👇
Weights: huggingface.co/poolside/Lagu…
API: platform.poolside.ai/
Blog: poolside.ai/blog/laguna-a-de…
✨ Excited to be at @NeurIPSConf in San Diego next week with the team at @poolsideai ⛱️ Booth #913!
If you’re building, researching, or thinking about the next wave of AI systems, especially around RL and agentic workflows, I’d love to connect.
Ping me if you’re around! ✨
3
184
Better late than ever, finally, code is available🙂
💻github.com/huawei-noah/noah-…
Happy to share our work on "Text2Code Generation with Modality-relative Pre-training" w/ @gcsanity & @glampouras_NLP, accepted at #EACL2024! 🎉
We propose to treat code and natural language as
different modalities.
📜arxiv.org/abs/2402.05783
💻coming soon (pending int. review)
Fenia Christopoulou retweeted
Research Scientist (permanent) positions just opened in our NLP team in London - Huawei Noah's Ark Lab! Looking for experienced researchers to help us tackle some interesting (and persistent) questions :)
Take a look and apply if interested:
huaweiuk.teamtailor.com/jobs…
Fenia Christopoulou retweeted
Delighted to present our #naacl2024 paper, #HumanRankEval: Automatic Evaluation of #LMs as Conversational Assistants with @glampouras_NLP and @iiacobacNLP providing fast, reliable and private evaluation of instruction-tuned #LLMs. A truly new eval paradigm, no #gpt4-as-a-judge :)
Checkout our latest work!
🚀 Excited to share our new pre-print: "Human-like Episodic Memory for Infinite Context LLMs"! We introduce EM-LLM, a novel approach integrating cognitive science insights into LLMs for vastly extended context processing: arxiv.org/pdf/2407.09450
What we did:
· 📊 We treat LLMs' K-V cache as analogous to personal experiences and segmented it into events of episodic memory based on Bayesian surprise (or prediction error).
· 🔍 We then apply a graph-theory approach to refine these events, optimizing for relevant information during retrieval.
· 🔄 When deemed important by the LLM's self-attention, past events are recalled based on similarity to the current query, promoting temporal contiguity & asymmetry, mimicking human free recall effects.
· ✨ This allows LLMs to handle virtually infinite contexts more accurately than before, without retraining.
Our method outperforms the SOTA model InfLLM on LongBench, given an LLM and context window size, achieving a 4.3% overall improvement with a significant boost of 33% on PassageRetrieval. Notably, EM-LLM's event segmentation also strongly correlates with human-perceived events!!
We are releasing this method today with our first set of results, but more results and analysis are coming soon.
Huge thanks to all my co-authors/colleagues for this amazing collaboration: Martin A Benfeghoul, Adnan Oomerjee, @fenchri, @glampouras_NLP, @hbouammar from @Huawei Noah's Ark and Jun Wang from @UCL.
For a fuller description, check out @hbouammar's thread: nitter.cf/hbouammar/status/18127…
Stay tuned for more updates and a code release soon :) #LLMs #LongContextLLMs #EpisodicMemory #NLP #CogSci #MachineLearning #AI
13
616
So happy to be back to MCR for this talk! Thanks again for the invitation!
After a short break, Dr Fenia Christopoulou (@fenchri), Research Scientist at @Huawei Noah’s Ark Lab, presents on Natural and Programming Language Models! 🦾 #ADSAI2024 @nactem_unimcr






















