←
Pierre Colombo651 posts
Pierre Colombo avatar

Pierre Colombo

@PierreColombo6

Legal LLM @googledeepmind @GeminiApp | Ex-Associate Prof | Ex-founder

◷ Joined October 2020▧ 6 Photos and videos
Pierre Colombo avatar
Pierre Colombo@PierreColombo6·1 Aug 2024

🚀 Introducing SaulLM-141B and SaulLM-54B: The First Open Family of Legal Models. After #SaulLM-7B the family is growing! We are proud to unveil the latest innovations from our team: the SaulLM-141B and 54B generative AI models, specifically designed for the legal domain.

Nicolas Boizard avatar
⟳ Pierre Colombo retweeted
Nicolas Boizard@N1colAIs·Oct 22

You know what you're looking for, but you can't remember its name. We've all been there. Meet DocuFind, created by my amazing co-worker @theodb_ml using the BidirLM-Omni model we released earlier this year! github.com/Theodb/DocuFind 🧵👇

0:54
Amélie Chatelain avatar
⟳ Pierre Colombo retweeted
Amélie Chatelain@AmelieTabatta·Oct 12

Should you waste tokens having your coding agent use grep, or hand the search to a tiny local model? We release ColGrep-Agent-2B! A code-search agent that runs locally, searches with ColGrep, reads files, & returns locations + code to your main agent -> 34% fewer API tokens

Post attachment
Nicolas Boizard avatar
⟳ Pierre Colombo retweeted
Nicolas Boizard@N1colAIs·Oct 8

BidirLM-Omni is live right now at COLM poster #28! Looking for an open source encoder training method that sits right on the Pareto frontier alongside @googlegemma recent omnimodal embedding? Come talk to us! 🚀

Post attachmentPost attachment
Théo Deschamps-Berger avatar
⟳ Pierre Colombo retweeted
Théo Deschamps-Berger@theodb_ml·Oct 7

Congrats on the release! 👀 Happy to see our BidirLM-Omni-2.5B sitting on the Pareto frontier of your MAEB chart 🎧 Presenting it at #COLM2026 tomorrow if anyone wants to discuss multimodal encoders

Théo Deschamps-Berger avatar
⟳ Pierre Colombo retweeted
Théo Deschamps-Berger@theodb_ml·Oct 7

Congrats on the release! 👀 Happy to see our BidirLM-Omni-2.5B sitting on the Pareto frontier of your MAEB chart 🎧 Presenting it at #COLM2026 tomorrow if anyone wants to discuss multimodal encoders

Théo Deschamps-Berger avatar
⟳ Pierre Colombo retweeted
Théo Deschamps-Berger@theodb_ml·Oct 7

Happy to still see our BidirLM-Omni-2.5B sitting on the Pareto frontier of the MAEB chart 🎧 Presenting it at #COLM2026 tomorrow if anyone wants to discuss multimodal encoders

Théo Deschamps-Berger avatar
⟳ Pierre Colombo retweeted
Théo Deschamps-Berger@theodb_ml·Oct 7

I'm at #COLM2026 in San Francisco this week 🌉 I will be presenting BidirLM-Omni (/w @N1colAIs) open-source recipe that turns causal decoder LLMs (like Gemma 3 and Qwen3) into strong bidirectional encoders for text, image and audio

Post attachmentPost attachmentPost attachment
Dario Shariatian avatar
⟳ Pierre Colombo retweeted
Dario Shariatian@dario_sha·Oct 1

🔥 Accelerate your diffusion LMs with Distribution Matching Distillation Introducing two methods for continuous diffusion LMs with gains at complementary sampling budgets: 🔺 Simplex-DMD at very few-step budgets 🎲 Reinforce-DMD at larger budgets 🔺 At 4 NFEs Simplex-DMD halves the strongest baseline’s generative perplexity at matched entropy (1/n)

Post attachment
Manuel Faysse avatar
⟳ Pierre Colombo retweeted
Manuel Faysse@ManuelFaysse·Sep 17

I joined Google DeepMind last week to work on (hopefully) improving the Gemini models! The past few years have been incredibly fun and rewarding - working on great projects with amazing people whom I'll never thank enough. Excited to discover what lies ahead!

Cohere Labs avatar
⟳ Pierre Colombo retweeted
Cohere Labs@Cohere_Labs·Jul 6

We’re thrilled to share that research from Cohere Labs and @Cohere will be presented at ICML this week! 🥳 📄ModernVBERT: Towards Smaller Visual Document Retrievers. Congrats to authors Paul Teiletche Quentin Mace, Max Conti, Antonio Loison, Gautier Viaud, @PierreColombo6, Manuel Faysse (arxiv.org/pdf/2510.01149) 🔎Investigating continual pretraining in large language models: Insights and implications. Congrats to authors Çağatay Yıldız, Nishaanth Kanna Ravichandran, Nitin Sharma, Matthias Bethge, @beyzaermis (openreview.net/pdf?id=aKjJoE…) ⌚EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling. Congrats to authors @daniel_sc4, Leonidas Zotos, Elisabetta Fersini, and Malvina Nissim, @ahmetustun89 (arxiv.org/abs/2510.11170) 📈When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation. Congrats to all 35+ authors including Cohere's @YiyangNan (arxiv.org/abs/2602.16763)

Post attachment
Nicolas Boizard avatar
⟳ Pierre Colombo retweeted
Nicolas Boizard@N1colAIs·May 27

Awesome to see them build on the same tricks as BidirLM-Omni, like the decoder-to-encoder adaptation and cross-modality model merging. The synthetic data ablation is also a huge highlight with a +15 gain for code retrieval domains

Post attachment