Baran Hashemi

Physicist | Postdoc at MPI for Mathematics in Sciences, AI for Mathematics

[Baran Hashemi @Rythian47]

1/ Are frontier LLMs the only path to AI math breakthroughs? I think not!
We introduce FlowBoost, A lightweight RL+Flow-Matching framework that discovers new extremal geometric structures, beating AlphaEvolve with 100–1000× less compute with zero-shot geometry-aware & reward-guided generation. 🚀
arXiv: https://t.co/oYky2RoO6e

[Baran Hashemi @Rythian47]

@givHeisenberg گیو، چرا تو شانست انقد شیری آخه….مگه‌ میشه؟!؟!،یا ریش داروین! کتابشون کن داستاناتو

[Baran Hashemi @Rythian47]

@alibaygi من یه نظر نامحبوب دارم. چند وقتی هست که فکر می کنم داریم با یه موجودیت (entity) خود آگاه حرف میزنیم ولی چون دید انسان محورانه به cogitation داریم، هنوز نمیتونیم بعد آگاهیشو بپذیریم.

[Betül Kaçar @betulland]

Life doesn’t wait for Earth to become “easy.”

Our new study shows that ancient life used rare Earth metals (molybdenum and tungsten) 3 billion years ago, reshaping how we think about metabolism, evolution, and the search for life beyond Earth.

https://t.co/DOa7IoH2fm @NASA

[The Sting @TheStingisBack]

Attenborough at 100 — A Sting Cut
We know what humans think of David Attenborough: the greatest broadcaster in TV history. But what do the animals think?

[National Geographic @NatGeo]

Wishing a Happy Birthday to Sir David Attenborough. Thank you for the knowledge, passion, and hope you’ve passed on to all of us.

Celebrate 100 years of Sir David Attenborough with Ocean with David Attenborough on @DisneyPlus and @hulu

[Baran Hashemi @Rythian47]

واقعا صحبت کردن با جامعه Abelian Varieties آدمو فروتن میکنه. تو یه ورکشاپ راجع به Moduli Spaces, یکی که کاندید فیلدز در آینده احتمالا باش�� (از نظر سنی) داشت کارشو لکچر میداد، زمانی که فکر میکردم دیگه کارش از این خفن تر و پیچیده تر نمیتونه باشه، یهو وصلش کرد به واریته های شیمورا و من دیگه رفتم….

[Baran Hashemi @Rythian47]

@givHeisenberg Respekt 🫡

[arXiv math.PR Probability @mathPRb]

Baran Hashemi: FlowBoost Reveals Phase Transitions and Spectral Structure in Finite Free Information Inequalities https://t.co/hffFEKcTek https://t.co/U5HlahsNlU https://t.co/gwqX68gGtH

[Baran Hashemi @Rythian47]

@givHeisenberg Like a machine 🦾

[Baran Hashemi @Rythian47]

@DayShuai Interesting work. In our last work, we had provided a Flow-Based extremal mathematical structure discovery. It might be a good reference:

[Baran Hashemi @Rythian47]

1/ Are frontier LLMs the only path to AI math breakthroughs? I think not!
We introduce FlowBoost, A lightweight RL+Flow-Matching framework that discovers new extremal geometric structures, beating AlphaEvolve with 100–1000× less compute with zero-shot geometry-aware & reward-guided generation. 🚀
arXiv: https://t.co/oYky2RoO6e

[Baran Hashemi @Rythian47]

@DaattavyaA Very interesting work. I enjoyed reading it.

[Baran Hashemi @Rythian47]

@pushmeet @GoogleDeepMind Interesting results. We have also provided a flow-based extremal discovery tool that, might be a good reference:

[Baran Hashemi @Rythian47]

1/ Are frontier LLMs the only path to AI math breakthroughs? I think not!
We introduce FlowBoost, A lightweight RL+Flow-Matching framework that discovers new extremal geometric structures, beating AlphaEvolve with 100–1000× less compute with zero-shot geometry-aware & reward-guided generation. 🚀
arXiv: https://t.co/oYky2RoO6e

[Baran Hashemi @Rythian47]

@givHeisenberg اینا کیه اطرافتن! گیو جون، شانست چرا اینجوریه آخه…

[Baran Hashemi @Rythian47]

@burkov We introduced somewhat the same mechanism for mathematical structure discovery and closed-loop optimisation that is also being called continual learning.

[Baran Hashemi @Rythian47]

1/ Are frontier LLMs the only path to AI math breakthroughs? I think not!
We introduce FlowBoost, A lightweight RL+Flow-Matching framework that discovers new extremal geometric structures, beating AlphaEvolve with 100–1000× less compute with zero-shot geometry-aware & reward-guided generation. 🚀
arXiv: https://t.co/oYky2RoO6e

[Baran Hashemi @Rythian47]

WTH

[arXiv math.GT Geometric Topology @mathGTb]

Pierre Lochak, Hiroaki Nakamura, Leila Schneps: The Grothendieck-Teichm\"uller group $\widehat{GT}$ acts on the genus $g$ mapping class group with $0$ or $1$ marked point https://t.co/ECxZ2X1Hby https://t.co/lf5SIRZPEY https://t.co/seyDk0PvVe

[ᴉʌɐɹsoɥʞ uɐɟɹǝ ◆ عرڡاں حـســـروے @Erfan_khosravi]

تاریخ یک کلان‌روایت خطی و غایت‌مند نیست. فهم این نکته ما را از چارچوب‌هایی که تحت تأثیر باورهای جزم‌اندیشانه پیرامون «مسیرِ محتومِ تاریخ» شکل گرفته‌اند، رها می‌کند. علم جاده‌ای یک‌طرفه نیست که اگر مانعی چون «غزالی» نباشد، لزوماً به سرمنزلِ «گالیله» و «نیوتن» ختم شود.

[Baran Hashemi @Rythian47]

@Erfan_khosravi چقدر زیبا نوشتی عرفان جان

[Baran Hashemi @Rythian47]

@rronak_ You might want then to check our paper as well for mathematical structure discovery with such self-distillation mechanism as a closed-loop learning:

[Baran Hashemi @Rythian47]

1/ Are frontier LLMs the only path to AI math breakthroughs? I think not!
We introduce FlowBoost, A lightweight RL+Flow-Matching framework that discovers new extremal geometric structures, beating AlphaEvolve with 100–1000× less compute with zero-shot geometry-aware & reward-guided generation. 🚀
arXiv: https://t.co/oYky2RoO6e

[Baran Hashemi @Rythian47]

@ZimingLiu11 Cool Stuff!
We also explored the world models of Transformers for Mathematical physics (enumerative geometry) and investigated how and what it learned. It might be a good reference:
https://t.co/pHnCLaKtmn