Ievgen Redko

ML lead at Paris Noah's Ark Lab

Donate to the Ukrainian army:

[Ievgen Redko @IevgenRedko]

Following numerous requests, we've decided to extend the submission deadline for the @NeurIPSConf workshop on Recent Advances in Time Series Foundation Models!

📜New deadline: August 29
🌐 Openreview link: https://t.co/dQafx2sC2A

[Ievgen Redko @IevgenRedko]

Excited to announce a call for papers for our workshop on time series foundation models @NeurIPSConf, with an amazing lineup of speakers.

See the post below for more details on where to submit (deadline: 22nd of August).

[Ambroise Odonnat @AmbroiseOdonnat]

🚀 We are happy to organize the BERT²S workshop @NeurIPSConf 2025 on Recent Advances in Time Series Foundation Models.
🌐 https://t.co/RI2hENcDZW
📜Submit by August 22
🎓Speakers and panelists: @ChenghaoLiu15 Mingsheng Long @zoe_piran @danielle_maddix @atalwalkar @qingsongedu

[Simon Roschmann @SimonRoschmann]

How can we circumvent data scarcity in the time series domain?

We propose to leverage pretrained ViTs (e.g., CLIP, DINOv2) for time series classification and outperform time series foundation models (TSFMs).

📄 Preprint: https://t.co/3at0eaVsEL
💻 Code: https://t.co/GbmqJUuQyI

[Cohere Labs @Cohere_Labs]

Our ML Theory group is looking forward to welcoming @AmbroiseOdonnat next week on Thursday, June 19th for a session on "Large Language Models as Markov Chains"

[Richard Woodruff 🇺🇦 @frontlinekit]

This is incredible!! Way to go America 🇺🇲

Supporters of Ukraine have unfurled the world's largest Ukrainian flag on the White House ellipse, pushing for the U.S. to continue its aid against the russian invasion: "Do not abandon Ukraine!"

[Mathieu Blondel @mblondel_ml]

Full speech subtitled in English.

https://t.co/63rh8iProZ

[Mathieu Blondel @mblondel_ml]

Powerful speech by a French senator.

https://t.co/PiTlbIZI8u

[Leleka Foundation 🇺🇦 Лелека-Україна @Leleka_FDN]

The death toll won’t wait.

While the Trump administration has paused U.S. military aid to Ukraine, and medical supplies were withheld from military logistics, frontline medics are still fighting to save lives.

Support Leleka Foundation to help them.
https://t.co/lA76hEc6Ka

[Ostap Yarysh @OstapYarysh]

While President Trump was speaking to Congress about Russia’s signals for peace, Russia attacked Ukrainian cities with over 180 drones and ballistic missiles, destroying homes and killing civilians. The only signals Ukrainians heard tonight were air raid sirens and explosions.

[Timothy Snyder @TimothyDSnyder]

Countless emails asking how Americans can directly aid Ukrainian soldiers. Here’s an easy answer:
https://t.co/esLMTa8fn2

[Ievgen Redko @IevgenRedko]

Kudos to @Vasya2104 who led this project! Let us know if you used MANTIS by putting a star on
https://t.co/NNinTkphH9
and feel free to open PRs or issues if something is wrong.

[Ievgen Redko @IevgenRedko]

Our team open-sourced MANTIS: a foundation model for time series classification. It is lightweight, more efficient than competitors, and supports feature extraction mode without fine-tuning.

Arxiv: https://t.co/PPGoWdHcIw
Code: https://t.co/cM9ELd5oKj

A quick thread 👇

[Ievgen Redko @IevgenRedko]

Finally, MANTIS efficiently runs on high-dimensional datasets due to the natural support of fine-tunable adapters

[Giuseppe Paolo @_GPaolo]

Living organisms organize as loosely coupled hierarchies—while our AI systems remain rigid monoliths.

What if we built AI that scales and adapts like biological systems instead?
What would an AI like this look like? 🧵

1/9

[Romain Tavenard @rtavenar]

Come work with us on tslearn in beautiful Rennes!

(deadline for application is soon!)

https://t.co/Mv3SAEtjL4

[Oussama Zekri @oussamazekri_]

🚀 Policy gradient methods like DeepSeek’s GRPO are great for finetuning LLMs via RLHF.

But what happens when we swap autoregressive generation for discrete diffusion, a rising architecture promising faster & more controllable LLMs?

Introducing Score Entropy Policy Optimization (SEPO) !

"𝐅𝐢𝐧𝐞-𝐓𝐮𝐧𝐢𝐧𝐠 𝐃𝐢𝐬𝐜𝐫𝐞𝐭𝐞 𝐃𝐢𝐟𝐟𝐮𝐬𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬 𝐰𝐢𝐭𝐡 𝐏𝐨𝐥𝐢𝐜𝐲 𝐆𝐫𝐚𝐝𝐢𝐞𝐧𝐭 𝐌𝐞𝐭𝐡𝐨𝐝𝐬"

📑 https://t.co/TiqPzHbvML

Let’s dive in! 🧵👇

[Ambroise Odonnat @AmbroiseOdonnat]

🚀Proud to share our work on the training dynamics in Transformers with @_Vassim & @CabannesVivien @Inria @AIatMeta!

📝Easing Optimization Paths https://t.co/PGdku9ax4o (accepted @ICASSP 2025 🥳)

📝Clustering Heads 🔥https://t.co/kpWwO9xxQK

🖥️ https://t.co/WdB0MPD9pS

1/🧵