Omni-modal AI researcher. Creator of ColPali, BidirLM-omi, EuroBERT & EuroLLM. Ex-Prof@ Centrale (Paris-Saclay) · Ex-CSO@ https://xitter.cf/t.co/ncQ9gT2rpk (legaltech - SaulLM)
Joined October 2020
- Tweets649
- Following1.2K
- Followers550
- Likes1.3K
Pierre Colombo retweeted
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
Pierre Colombo retweeted
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! 🚀
Pierre Colombo retweeted
The one and only Michael Jordan was interviewed last week by the French newspaper Libération. Here is an English translation. Enjoy!
di.ens.fr/~fbach/MJordan_ITW…
Pierre Colombo retweeted
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
Pierre Colombo retweeted
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
Pierre Colombo retweeted
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
Pierre Colombo retweeted
🔥 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)
Pierre Colombo retweeted
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!
Pierre Colombo retweeted
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)
Pierre Colombo retweeted
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
Pierre Colombo retweeted
Gemini Embedding 2 is out, and it's completely omnimodal 😎
Great to see the next chapter of encoders heading toward text, audio, and visual unlocking so many use cases
arxiv.org/abs/2605.27295
Pierre Colombo retweeted
👏 Congratulations to @cohere on Command A+ — a powerful new model optimized for NVIDIA Blackwell and trained using NVIDIA CUDA-X libraries.
Proud to be a part of it!
Learn more ⤵️
Pierre Colombo retweeted
Releasing open-source under the Apache 2.0 license. We want to give developers direct access to enterprise-grade agentic capabilities from experimentation to production.
Sovereign AI. For all.
Download Command A+: huggingface.co/CohereLabs/co…
Or learn more: cohere.com/blog/command-a-pl…
Pierre Colombo retweeted
Cohere launches open weights model Command A+ that achieves 37 on the Artificial Analysis Intelligence Index
The release of Command A+ places @Cohere in line with Claude 4.5 Haiku on the Intelligence Index, and just above NVIDIA Nemotron 3 Super and Gemini 3.1 Flash-Lite.
Key Takeaways:
➤ Command A+ ranks first on AA-Omniscience Non-Hallucination at 86%, ~3 percentage points ahead of the next-best model. Its AA-Omniscience Accuracy is 9%, so the headline AA-Omniscience score lands at -4, demonstrating a similar archetype to Claude 4.5 Haiku, where the model knows its limits
➤ On Cohere’s API, Command A+ (~281 output tokens per second) is faster than several comparable open-weights and small to mid-sized proprietary models (e.g., GPT-5.4 nano, Claude 4.5 Haiku, and Grok 4.3), but still slower than Gemini 3.1 Flash-Lite Preview, which outputs 304 tokens per second
➤ Command A+ trails its peer set on scientific reasoning (HLE ~11%, GPQA Diamond ~76%) and on coding (Terminal-Bench Hard ~25%, SciCode ~38%), consistent with gaps on the hardest science and agentic coding benchmarks
➤ It supports visual reasoning and scores 63% on MMMU-Pro (between Claude 4.5 Haiku at 59% and GPT-5.4 nano (xhigh) at 65%)
Pierre Colombo retweeted
🚨 Do LLMs need to store everything they read in memory?
To reduce KV cache size and improve decoding speeds, we propose Self-Pruned KV attention, a mechanism where the model learns to decide which KVs to write in the persistent KV cache, discarding all the rest! @AIatMeta🧵
Pierre Colombo retweeted
@JinaAI_ has hopped on the omnimodal train🚂
They just dropped a collection of two Omni embedding models (0.9B & 2B). Similar to BidirLM, they seem to rely on the Qwen modality head for the larger one, while sticking with EuroBERT for the nano version 🥰
huggingface.co/collections/j…
Pierre Colombo retweeted
BidirLM-Omni is on MTEB and Sentence-Transformer!
huggingface.co/spaces/mteb/l…
🥇#1 Open-Source Model on MTEB (#15 overall)
🖼️#1 across all sizes on MIEB (Image)
🎧#1 sub-7B model on MAEB (Audio, #2 overall)
Small size, massive performance, Fully open
Model: huggingface.co/BidirLM
