Researcher at Imec AI Labs. Continual Learning Vision/LLMs. Prev. Postdoc. @Mila_Quebec, PhD @IP_Paris_
Berlin
Joined February 2015
- Tweets882
- Following764
- Followers1.3K
- Likes1.8K
The scientist used to stand between nature and human understanding. Tomorrow they will stand between AGI's understanding of nature and our own.
You can now navigate and explore the prompts that makes LLMs play better chess !
imec-ailabs.github.io/Automa…
Automatic prompt optimization (APO) is one of the most efficient levers for boosting LLM and agent performance — but measuring real gains is surprisingly tricky.
Glad to share from @imec_int AI.labs: "Benchmarking Prompt Optimization of Large Language Models With Chess"
🧵
Timothée Lesort retweeted
I recently moved to TU Darmstadt (Germany) and am currently hiring PhD student through ELISS.
ellis.eu/news/ellis-phd-prog…
If you interested, please apply and choose me as a potential advisor. Topics include Continual/Distributed/Federated/Active/Transparent AI.
Timothée Lesort retweeted
So happy to highlight one of the many applications of Botanic-1, our latest plant FM, on @googlegemma 's website !
teapawt.org/GoogleAI/status/210715…
Automatic prompt optimization (APO) is one of the most efficient levers for boosting LLM and agent performance — but measuring real gains is surprisingly tricky.
Glad to share from @imec_int AI.labs: "Benchmarking Prompt Optimization of Large Language Models With Chess"
🧵
10/11) Everything is public: the puzzles, the optimization and evaluation code, every raw observation behind the plots, and an interactive results explorer.
Paper: arxiv.org/abs/2610.00416
Code, data & results: github.com/imec-ailabs/Autom…
HF Dataset: huggingface.co/datasets/imec…
11/11) Joint work at imec AI.labs (Paris) with Alejandra López de Aberasturi Gómez, @karch_tristan , @TomVeniat , Philippe Modard, @karl_tuyls and @LudovicDenoyer . We hope it helps develop prompt optimization algorithms and improve the reasoning of models.
Timothée Lesort retweeted
Excited to announce our @COLM_conf workshop "Context Beyond the Window"!
We have a stacked lineup of speakers focusing on one of the most important topics today: context management.
Venue is non-archival; We welcome all relevant 4 or 8-page submissions!
teapawt.org/dvnxmvl_hdf5/status/20…
🚨Excited to announce our workshop Context Beyond the Window hosted at COLM in SF! 🚨
LLMs have finite context windows, yet real-world tasks demand absorbing, retaining, and acting on information that far exceeds any single prompt.
1/3
We're looking for submissions across:
context-beyond-window.github…
• Context compression 🧃 — token compaction, recursive subagent calls, and external memory for storing and retrieving information
• Efficient architectures 🚀 — sub-quadratic attention variants that make extremely long context computationally feasible
• Continual training 🌱 — test-time training on streaming data, context distillation, and knowledge accumulation through continued pre-training
• Agentic memory systems 🐘 — scaffolds and test-time scaling techniques that improve knowledge retention and acquisition in LLMs
• Evaluation 🎯 — benchmarking models on increasingly long-horizon tasks
ALT Modern language models operate within finite context windows, yet many real-world tasks require models to absorb, retain, and act on information that far exceeds any single prompt. This workshop addresses the full spectrum of context management: fitting more into the window, maintaining state across interactions, and transferring knowledge into parameters. We frame this around the trade-off between context-time memory (information supplied at inference) and weight-time memory (information absorbed into parameters). Our goal is to build a shared vocabulary across subcommunities that rarely meet in one venue: long-context modeling, retrieval-augmented systems, continual learning, knowledge distillation, and LLM agents.
Timothée Lesort retweeted
The DiLoCo team at Google DeepMind and Google Research is proud to release Decoupled DiLoCo, the next frontier for resilient AI pre-training.
Decoupled DiLoCo enables training with datacenters across the world, using heterogeneous hardware, and never halting the system despite hardware failures.
Timothée Lesort retweeted
(continual) pre-training is not dead!
some thoughts about cost per task (on cursorbench) being 2x lower, imo it can be due to:
- new base model: seems straightforward but it's not imo, you need to optimize the inference/training stack (both for rl and consumer inference), GLM-5 > V3.2 doesn't mean glm-5-base > V3, they may not be equally malleable to post/mid training
- more optimized kernel and inference stack/serving (most likely)
- rl/mid-training with objective/data to make smaller CoT (most likely)
- mid-training with more efficient arch: i would love for this to be true, and i can see how it's necessary if they use the previous base model generation and need efficient memory for long context, but since they also released some tricks with self-summary, i'd say unlikely? (they can and imo should be combined together for very long tasks)
Timothée Lesort retweeted
This week, we released a paper from Meta @AIatmeta
“MuLoCo: Muon is a practical inner optimizer for DiLoCo”, showing that K=1 MuLoCo has a Pareto-optimal performance-training-time tradeoff
Let’s drill deeper into single-worker MuLoCo’s efficiency 🧵1/5
teapawt.org/benjamintherien/status…
Are frontier LLMs trained across datacenters? One thing is certain: if the pre-training optimizer’s critical batch size is too small, they are NOT! Excited to announce MuLoCo, a pre-training optimizer that can efficiently pre-train across datacenters while having large enough batch sizes to warrant doing so. 🧵1/N
Timothée Lesort retweeted
I have open positions including Postdocs, PhD, master's students, and PhD interns. For more information eugenium.github.io/Projects/…