aahlad puli

606 posts

aahlad puli

aahlad puli

@aahladpuli

On the 25-26 job market! Faculty Fellow at NYU. AI/ML, OOD generalization, healthcare, causality. https://t.co/y011yiqnYn

New York, NY Katılım Aralık 2010
1.6K Takip Edilen578 Takipçiler
aahlad puli retweetledi
Todd Morrill
Todd Morrill@tee_oh_double_d·
Today I'm heading to San Diego for NeurIPS for the first time to present some research I've been working on. I got into machine learning about 10 years ago and always thought of NeurIPS as our field's Woodstock or Burning Man—the big one! I can't wait be in the mix! 1/N
English
2
1
1
234
aahlad puli
aahlad puli@aahladpuli·
Heading to neurips soon! I'm on the job market and I work on making AI reliable, with a focus on healthcare. Would love to meet people and hear about opportunities!
English
0
1
4
326
aahlad puli retweetledi
Tal Linzen
Tal Linzen@tallinzen·
Many CDS faculty fellows have gone on to take tenure-track positions at top universities! This is one case where correlation definitely equals causation: cds.nyu.edu/faculty-fellow…
English
1
1
2
1.4K
aahlad puli retweetledi
Tal Linzen
Tal Linzen@tallinzen·
Fellows work across all areas of research at CDS. I've personally enjoyed collaborating with past and current fellows in natural language and cognitive science (@najoungkim, @byungdoh, @ravfogel, and others!).
English
1
1
3
709
aahlad puli retweetledi
Zachary Horvitz
Zachary Horvitz@zachary_horvitz·
✨Masked Diffusion Language Models✨ are great for reasoning, but not just for the reasons you think! Fast parallel decoding? 🤔 Any-order decoding? 🤨 Plot twist: MDLMs offer A LOT MORE for inference and post-training! 🎢🧵
Zachary Horvitz tweet media
English
4
38
162
21.6K
aahlad puli
aahlad puli@aahladpuli·
In Dyson's frogs/birds analogy, did he intend the subtext that the wells are all connected via groundwater?
English
0
0
1
133
aahlad puli
aahlad puli@aahladpuli·
AI peeps, what are your favorite AI for health papers from recent times?
English
1
1
3
303
aahlad puli retweetledi
Jatin Prakash
Jatin Prakash@bicycleman15·
What to do when you have zero rewards during RL? We benchmarked RL baselines on a simple star-graph task where they underperform in zero reward scenarios. Turns out, a dead simple data-centric intervention of just adding easy samples of the task helps unlock RL training! 👇
Jatin Prakash tweet media
Anirudh Buvanesh@AnirudhBuvanesh

Zero rewards after tons of RL training? 😞 Before using dense rewards or incentivizing exploration, try changing the data. Adding easier instances of the task can unlock RL training. 🔓📈To know more checkout our blog post here: spiffy-airbus-472.notion.site/What-Can-You-D…. Keep reading 🧵(1/n)

English
2
7
14
826
aahlad puli retweetledi
Polina Kirichenko
Polina Kirichenko@polkirichenko·
We are excited to announce a workshop on Demographic Diversity in Computer Vision (DemoDiv) at #CVPR2025! Submit your work studying various axes of demographic diversity and fairness in models and datasets and join us in Nashville in June! Deadline: March 31st
Polina Kirichenko tweet media
English
2
16
97
28.2K
aahlad puli retweetledi
Hesam Asadollahzadeh
Hesam Asadollahzadeh@HesamAsdz·
Excited to announce that the Spurious Correlation and Shortcut Learning (SCSL) workshop has been accepted to #ICLR2025! 🎉 Join us to explore cutting-edge research on these critical topics. Follow @SCSLWorkshop for updates and details!😉 openreview.net/forum?id=B5Mlq…
Luis Oala@LuisOala

2025 @iclr_conf workshops are now available at #tab-accept" target="_blank" rel="nofollow noopener">openreview.net/group?id=ICLR.… thank you to all the amazing teams that prepared proposals out of 120 strong submissions 40 proposals were selected for 2 days of workshops in singapore a blog post with links to workshop sites will follow

English
0
7
21
1.9K

Keşfet

@najoungkim @byungdoh @ravfogel @marikgoldstein @attentionmech @ElanRosenfeld @AdtRaghunathan @elonmusk