Noor Islam S. Mohammad @ICML-26

I am a graduate student in Computer Science at @itu1773 and @nyuniversity.

[European Conference on Computer Vision #ECCV2026 @eccvconf]

We are just 2 weeks away from kicking off #ECCV2026 and thrilled to share our exciting program with you all! This year we will have 3 keynotes from @ylecun, @Jamie_Shotton and Kristen Grauman, as well as 2 timely panels on AI in research!

Stay updated on https://t.co/WSoiwuIAzj

[Alireza Modirshanechi @modirshanechi]

Excited to share that I'll be starting as a junior professor and Emmy Noether awardee at the University of Göttingen this October! 🥳

🚀 I'll be hiring PhD students and postdocs across both ML and CogSci: https://t.co/SWO5gf4Y57

Please spread the word! 🙏

[Andrei Cimpian @AndreiCimpian]

Come join my lab at NYU as a postdoc! 😀

Apply here: https://t.co/Rdovvmbmiz

More about our work: https://t.co/b2mRhctYDN

[Artificial Intelligence Papers @SciFi]

Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering

Noor Islam S. Mohammad, Uluğ Bayazıt
https://t.co/cQ8BDjwiUe [𝚌𝚜.𝙰𝙸]

[Noor Islam S. Mohammad @ICML-26 @nislam_mohammad]

Excited to share our latest Paper:

“Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering”

Paper: https://t.co/CGRSgKUY6W
Project: https://t.co/2n0i22M7xJ

[Rosinality @rosinality]

https://t.co/ZR4U2vwbuM

Scaling law for RL that connects rewards and pretraining loss, RL compute, on a synthetic (chess moves) setting. It also leads to the answer to the very interesting question, given fixed compute, what is the optimal allocation between pretraining and RL.

[Nikita Kachaev @judokach]

🤯 The difference between #ICLR2026 and #ICML2026 poster sessions is wild!

Maybe that's what happens when thousands of researchers have to fly 20+ hours just to discuss posters

(just a fun image below)

[ICML Conference @icmlconf]

Arvind Narayanan @random_walker brings us a talk “What will be left for us to work on?” At #icml2026

[ICML Conference @icmlconf]

Congrats to the 2026 test of time award winners! #icml2026

[ICML Conference @icmlconf]

Closing out the technical program for the day, we have Susan Athey (@Susan_Athey) giving an invited talk on causal inference and transformer models.

[Noor Islam S. Mohammad @ICML-26 @nislam_mohammad]

In Seoul for ICML 2026 🇰🇷 Looking to connect with researchers for collaboration, research internship opportunities, and a prospective Ph.D. (Fall 2027). If you’re attending ICML or based in Seoul, let’s connect! 🤝

#ICML2026 #AI #MachineLearning #Research #PhD #Internship

[Noor Islam S. Mohammad @ICML-26 @nislam_mohammad]

We’re happily gathered in conference hall C1 for the exciting oral presentation of ICML-2026! 🇰🇷 My wonderful colleagues from China 🇨🇳 are also here with us.

[Noor Islam S. Mohammad @ICML-26 @nislam_mohammad]

I am looking forward to connecting with ICM.

[Noor Islam S. Mohammad @ICML-26 @nislam_mohammad]

I am looking forward to seeing and meeting with you all.

[ICML Conference @icmlconf]

Be sure to check out the picturesque Starfield Library! Also located within the Coex complex.

[Sohyeon Kim @ohmyksh]

For Seoulmaxxing @ ICML!

(New Updates)
- Naver Map: https://t.co/PVNcFdJHHu
- Vegetarian-Friendly Places: https://t.co/qezzmuq5Il

Check out the website for the latest updates and more details!

https://t.co/AdN1sHMg1I

[Noor Islam S. Mohammad @ICML-26 @nislam_mohammad]

https://t.co/O6eB7WrMBB

[Natural Language Processing Papers @HEI]

SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization

Noor Islam S. Mohammad, Ulug Bayazit
https://t.co/mlI6QRzNhX [𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙰𝙸]

[NeurIPS Conference @NeurIPSConf]

NeurIPS 2026 is recruiting Ethics Reviewers!

If you have experience critically evaluating potential risks and harms in machine learning research, and can provide thoughtful feedback on broader impacts, please read our Call for Reviewers (https://t.co/vkrxGLi5A6) and consider volunteering as an ethics reviewer. You can directly volunteer by filling the form here: https://t.co/lLao3AjqFq

Please share with your qualified and interested colleagues. As the scale of the conference continues to grow, so we are always seeking to grow our pool of ethics reviewers.

[Artificial Intelligence Papers @SciFi]

The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements

Noor Islam S. Mohammad, Tamim Sheikh
https://t.co/2RqmzLghjv [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]