Reyhane Askari (@ReyhaneAskari)

Pinned

R

Reyhane Askari@ReyhaneAskari · May 1

Deliberate practice is accepted to #ICML2025 as a spotlight (top 2.6%!) 🚀

RReyhane Askari@ReyhaneAskari · Feb 28

🚀 New Paper Alert! Can we generate informative synthetic data that truly helps a downstream learner? Introducing Deliberate Practice for Synthetic Data (DP)—a dynamic framework that focuses on where the model struggles most to generate useful synthetic training examples. 🔥…

1

18

152

53

16.0K

Pinned

R

Reyhane Askari@ReyhaneAskari · Jul 11

📢 We're organizing a #NeurIPS2025 workshop on generative modeling, learning to sample, and optimal transport / control. Two submission tracks this year! (deadline #Aug22) 📰 Call for 4-page paper on research / dataset 💡 Call for #Open #Question: 2-page proposal on open…

KKirill Neklyudov@k_neklyudov · Jul 11

1/ Where do Probabilistic Models, Sampling, Deep Learning, and Natural Sciences meet? 🤔 The workshop we’re organizing at #NeurIPS2025! 📢 FPI@NeurIPS 2025: Frontiers in Probabilistic Inference – Learning meets Sampling Learn more and submit → fpiworkshop.org…

0

12

93

17

6.0K

Reyhane Askari Retweeted

R

Reza Bayat@reza_byt · Jul 16

📄 New Paper Alert! ✨ 🚀Mixture of Recursions (MoR): Smaller models • Higher accuracy • Greater throughput Across 135 M–1.7 B params, MoR carves a new Pareto frontier: equal training FLOPs yet lower perplexity, higher few‑shot accuracy, and more than 2x throughput.…

2

54

233

147

21.0K

Reyhane Askari Retweeted

G

Gabriel Huang@GabrielHuang9 · Jul 15

As #ICML2025 kicks off in Vancouver, our AI talent is being quietly pushed out. 🇨🇦 We've been waiting 28 months for permanent residency, but @CitImmCanada won’t budge. Please read and share our story facebook.com/share/p/1AwU2f… linkedin.com/posts/gbxhuang… #IRCC #AI #Immigration #AI

3

10

22

0

5.0K

R

Reyhane Askari@ReyhaneAskari · Jul 16

Today at #ICML2025, we present Deliberate Practice: an approach to improve sample-efficiency by generating harder, not more, examples. - Oral talk at 10:45 - West Ballroom B | Orals 3C: Data-Centric ML Join us to discuss principled approaches to more efficient learning.

RReyhane Askari@ReyhaneAskari · Jul 16

Excited to present our work "Improving the scaling laws of synthetic data with deliberate practice", tomorrow at #ICML2025 📢 Oral: Wed. 10:45 AM 📍 West Ballroom B (Oral 3C Data-Centric ML) 🖼️ Poster: 🕚 11:00 AM – 1:30 PM 📍 East Exhibition Hall A-B (Poster Session 3 East)

0

6

16

4

2.0K

R

Reyhane Askari@ReyhaneAskari · Jul 16

Excited to present our work "Improving the scaling laws of synthetic data with deliberate practice", tomorrow at #ICML2025 📢 Oral: Wed. 10:45 AM 📍 West Ballroom B (Oral 3C Data-Centric ML) 🖼️ Poster: 🕚 11:00 AM – 1:30 PM 📍 East Exhibition Hall A-B (Poster Session 3 East)

RReyhane Askari@ReyhaneAskari · Feb 28

🚀 New Paper Alert! Can we generate informative synthetic data that truly helps a downstream learner? Introducing Deliberate Practice for Synthetic Data (DP)—a dynamic framework that focuses on where the model struggles most to generate useful synthetic training examples. 🔥…

0

9

37

6

4.0K

R

Reyhane Askari@ReyhaneAskari · Jul 14

Presenting CRM at #ICML2025 📌 Wednesday, 16th July, 11 am 📍East Exhibition Hall A-B (E-2101) Lets chat about distribution shifts! Been deep into causality & invariance based perspectives, and recently exploring robust LLM pretraining architectures.

DDivyat Mahajan@divyat09 · May 1

Happy to share that Compositional Risk Minimization has been accepted at #ICML2025 📌Extensive theoretical analysis along with a practical approach for extrapolating classifiers to novel compositions! 📜 arxiv.org/abs/2410.06303

0

9

49

7

4.0K

R

Reyhane Askari@ReyhaneAskari · Jul 8

Happy to share that our work has been accepted at #COLM2025! Use #SAS to steer your LLM in sparse spaces.

RReza Bayat@reza_byt · Mar 5

New Paper Alert!📄 "It’s better to be sparse than to be dense" ✨ We explore how to steer LLMs (like Gemma-2 2B & 9B) by modifying their activations in sparse spaces, enabling more precise, interpretable control & improved monosemanticity with scaling. Let’s break it down! 🧵

1

10

75

24

3.0K

Reyhane Askari Retweeted

Y

Yoram Bachrach@yorambac · Jul 7

AI Research Agents are becoming proficient at machine learning tasks, but how can we help them search the space of candidate solutions and codebases? Read our new paper looking at MLE-Bench: arxiv.org/pdf/2507.02554 #LLM #Agents #MLEBench

8

65

314

168

27.0K

R

Reyhane Askari@ReyhaneAskari · Jul 1

This new work generalizes the recent Adjoint Sampling approach from Stochastic Control to Schrodinger Bridges, enabling measure transport between data and unnormalized densities. Achieves SOTA on large-scale energy-driven conformer generation. See thread by @guanhorng_liu

GGuan-Horng Liu@guanhorng_liu · Jul 1

Adjoint-based diffusion samplers have simple & scalable objectives w/o impt weight complication. Like many, though, they solve degenerate Schrödinger bridges, despite all being SB-inspired. 📢 Proudly introduce #Adjoint #Schrödinger #Bridge #Sampler, a full SB-based sampler that…

1

21

127

47

9.0K

R

Reyhane Askari@ReyhaneAskari · Jun 27

The submission deadline for #SG2RL @ICCVConference Workshop has been extended to June 30th, 23:59 AoE. Looking forward to receiving your awesome submissions ✌️🤩 #ICCV2025 @TumCamp @fedassa @ir0armeni @eadeli @MunichCenterML

AAzade Farshad@azadef · Jun 21

#SG2RL returns to @ICCVConference 2025 at Honolulu, Hawai'i 🌴☀️ We call for full papers and extended abstracts on all topics around graphs and scene graphs. Deadline: 26 June (23:59PT) Website: sites.google.com/view/sg2rl With our amazing co-organizers: @eadeli @ir0armeni @fedassa

0

5

15

0

3.0K

Reyhane Askari Retweeted

U

Umut U. Simsekli@umutsimsekli · Jun 23

Anyone from #iran looking for a phd/postdoc/research internship in statistical learning theory, deep learning theory etc, contact me. Please retweet.

4

51

101

17

17.0K

Reyhane Askari Retweeted

A

Azade Farshad@azadef · Jun 21

#SG2RL returns to @ICCVConference 2025 at Honolulu, Hawai'i 🌴☀️ We call for full papers and extended abstracts on all topics around graphs and scene graphs. Deadline: 26 June (23:59PT) Website: sites.google.com/view/sg2rl With our amazing co-organizers: @eadeli @ir0armeni @fedassa

1

4

12

1

10.0K

Reyhane Askari Retweeted

R

Richard Sutton@RichardSSutton · Jun 18

In war, both sides lose. That we don’t learn this is the greatest tragedy.

26

47

511

25

31.0K

Reyhane Askari Retweeted

W

WiML@WiMLworkshop · Jun 12

🚨 Applications are now open for WiML Symposium @ ICML 2025! 📍 Vancouver, Canada 📅 July 16, 2025 🎓 Present a poster 🙋 Volunteer ☕ Connect & network at talks, panels, and socials 📌 Deadline: June 25 (AoE) 📝 Apply now: tinyurl.com/3dbesr9t #WiML #ICML2025

5

6

14

2

2.0K

Reyhane Askari Retweeted

R

ReGenAI Workshop@ReGenAIWorkshop · Jun 11

Join us Thursday afternoon in Room 106A for a great set of speakers, panelists, and contributed works focused on Responsible Generative AI @CVPR!! #CVPR2025

1

5

6

0

2.0K

Reyhane Askari Retweeted

P

Polina Kirichenko@polkirichenko · Jun 10

Join us at #CVPR2025 Demographic Diversity in Computer Vision workshop tomorrow! 📅 Wednesday, June 11, 9am-6pm 📍 room 213 (main session) + Hall D (poster sessions), the Music City Center We have an amazing lineup of speakers and panelists! Can't wait to meet you all there :)

3

22

92

6

17.0K

Reyhane Askari Retweeted

R

ReGenAI Workshop@ReGenAIWorkshop · Jun 6

Less than one week away from the 2nd Workshop on Responsible Generative AI @CVPR! It’ll be on Thursday afternoon, and we’ve got a great set of presenters and participants! Check out the program & accepted work: sites.google.com/view/cvpr-resp… See you in Nashville! 🎶 #cvpr2025

0

3

4

0

325

R

Reyhane Askari@ReyhaneAskari · Jun 3

Today marks a big milestone for me. I'm launching @LawZero_, a nonprofit focusing on a new safe-by-design approach to AI that could both accelerate scientific discovery and provide a safeguard against the dangers of agentic AI.

LLawZero - LoiZéro@LawZero_ · Jun 3

Every frontier AI system should be grounded in a core commitment: to protect human joy and endeavour. Today, we launch @LawZero_, a nonprofit dedicated to advancing safe-by-design AI. lawzero.org

133

187

858

153

96.0K

R

Reyhane Askari@ReyhaneAskari · May 28

The deadline is postponed to June 2!

CCoLLAs 2025@CoLLAs_Conf · Apr 7

🌟 New at CoLLAs2025! 🌟 We’re inviting applications for our Early-Career Spotlight Program—a chance for rising researchers to present their vision & trajectory in lifelong learning. 📅 Apply by May 26, 2025 📢 30-min invited talk + blog feature 🔗 lifelong-ml.cc/Conferences/20……

0

1

5

0

653