Franck Lebeau @_Kcnarf

#AI in #NLP, dataviz expert, full stack dev, math_art and day-to-day enthusiast; also, PhD in CS, and trying to reduce my environmental footprint Joined December 2016

Tweets

4K
Followers

564
Following

413
Likes

4K

Amir Zur @AmirZur2000

a month ago

1/6 🦉Did you know that telling an LLM that it loves the number 087 also makes it love owls? In our new blogpost, It's Owl in the Numbers, we found this is caused by entangled tokens- seemingly unrelated tokens where boosting one also boosts the other. owls.baulab.info

18 72 662 67K 465

tomaarsen @tomaarsen

a month ago

😎 I just published Sentence Transformers v5.1.0, and it's a big one. 2x-3x speedups of SparseEncoder models via ONNX and/or OpenVINO backends, easier distillation data preparation with hard negatives mining, and more! See 🧵for the deets:

1 15 132 5K 43

Download Image

Antoine Chaffin @antoine_chaffin

a month ago

Obviously it has been catched by @_reachsumit before the official announcement! 😁 I am very happy to announce that PyLate has now an associated paper and it has been accepted to CIKM! Very happy to share this milestone with my dear co-creator @raphaelsrty 🫶

Sumit @_reachsumit

a month ago

0 7 47 6K 24

3 7 39 4K 9

Franck Lebeau @_Kcnarf

a month ago

🤔Do you know that LLMs produce probabilities among each available token of the vocabulary. Only after comes the choice of the final outputed token. 👌Here is crystal clear, yet insightful, explanations of the various technics used to choose the next token

AI Coffee Break with Letitia @AICoffeeBreak

a month ago

1 8 38 2K 23

Download Image

0 1 3 375 1

Florian Tramèr @florian_tramer

a month ago

Are hallucinated references making it to arXiv? Yes, definitely! Since the release of Deep Research in February bogus references are on the rise (coincidence?) I wrote a blog post (link below) on my analysis (which hugely underestimates the true rate of hallucinations...)

9 27 286 33K 87

Download Image

Franck Lebeau @_Kcnarf

a month ago

TLDR : 𝐀𝐈 + 𝐆𝐨𝐨𝐝 𝐕𝐒 𝐁𝐚𝐝 engineer Good engineer + AI ≥ 10* good Engineer ≥ 100* bad engineer + AI

Santiago @svpino

a month ago

TLDR : 𝐀𝐈 + 𝐆𝐨𝐨𝐝 𝐕𝐒 𝐁𝐚𝐝 engineer Good engineer + AI ≥ 10* good Engineer ≥ 100* bad engineer + AI

184 175 2K 106K 274

0 0 0 27 0

Jo Kristian Bergum @jobergum

a month ago

I think more AI builders now recognize that the core quality concern is context confusion, not context window length limitations. Lots of agent implementations now let users compress context to avoid quality degradation.

8 5 77 7K 16

Adam Rackis @AdamRackis

a month ago

From the AI workshop I'm in: "The S in MCP stands for security"

46 183 2K 129K 172

Yung-Sung Chuang @YungSungChuang

a month ago

Scaling CLIP on English-only data is outdated now… 🌍We built CLIP data curation pipeline for 300+ languages 🇬🇧We train MetaCLIP 2 without compromising English-task performance (it actually improves! 🥳It’s time to drop the language filter! 📝arxiv.org/abs/2507.22062 [1/5] 🧵

3 80 292 21K 125

Download Image

Franck Lebeau @_Kcnarf

a month ago

Je plussoie

Steve Krouse @stevekrouse

a month ago

Je plussoie

91 148 948 234K 482

Download Image

0 0 0 32 0

Datawrapper @Datawrapper

a month ago

📊 In this week's Data Vis Dispatch: U.S. tariffs, humanitarian crisis in Gaza, and much more. 🗞️ datawrapper.de/blog/data-vis-…

0 1 5 917 1

Download Image

Franck Lebeau @_Kcnarf

2 months ago

Imho, this illustrates current 𝑨𝑰 𝒄𝒐𝒎𝒑𝒆𝒕𝒆𝒏𝒄𝒚, which is distinct from intelligence

Stated Clearly - Jon Perry @StatedClearly

2 months ago

Imho, this illustrates current 𝑨𝑰 𝒄𝒐𝒎𝒑𝒆𝒕𝒆𝒏𝒄𝒚, which is distinct from intelligence

88 233 3K 405K 767

Download Video

0 0 0 69 1

Etienne Jacob @etiennejcb

2 months ago

I’ve been exploring physarum-style simulations on and off for a long time, and I finally wrote an article sharing the techniques I’ve been using. It ranges from the classic physarum algorithm to some of my own weird tricks. I hope you enjoy it! bleuje.com/physarum-expla…

8 41 321 21K 220

Raphaël Sourty @raphaelsrty

2 months ago

With @LightOnIO we are thrilled to release pylate-rs 🚀⭐️ An efficient inference engine for late-interaction models written in Rust and based on Candle ⚡️ pylate-rs is the best Python library / Rust crate / NPM package to spawn late-interaction models in milliseconds.

5 17 102 27K 62

LightOn @LightOnIO

2 months ago

🏎️ Introducing PyLate-rs @raphaelsrty is back at it to make you love late-interaction models! After quickening the retrieval process with FastPlaid, he’s now making inference lightning-fast with this lightweight tool crafted in Rust for optimal speed and efficiency! 💫And…

Raphaël Sourty @raphaelsrty

2 months ago

5 17 102 27K 62

0 16 52 5K 28

Download Image

Antoine Chaffin @antoine_chaffin

2 months ago

I'll be covering Reason-ModernColBERT in tonight's presentation, so please come if you are interested! maven.com/p/1973fe/going… (And please be gentle, this is the first time I will be speaking live in front of this many people 😭)

Victoria Slocum @victorialslocum

2 months ago

11 90 504 37K 534

Download Image

5 14 87 6K 60

Victoria Slocum @victorialslocum

2 months ago

Looking for a cheaper, open source alternative to agentic RAG? Try multi-vector retrieval with Reason-ModernColBERT. Most search systems compare one big summary vector per document. Multi-vector retrieval is different - it keeps separate vectors for each word or phrase, then…

11 90 504 37K 534

Download Image

Franck Lebeau @_Kcnarf

2 months ago

I'm totally in. Hallucination is the open door to Creativity. Anyone can use it, or close it (for better accuracy). But adhering to whatever the user says is the closed door to critical thinking. Yet noone as the key to open it.