nlp_pranav's profile picture. not active on this site

Pranav

@nlp_pranav

not active on this site

Pranav reposted

It is PhD application season again 🍂 For those looking to do a PhD in AI, these are some useful resources 🤖: 1. Examples of statements of purpose (SOPs) for computer science PhD programs: cs-sop.org [1/4]


I'm researching how ACL's peer review policies impact NLP research quality, career trajectories, and inclusivity within our community. I am running a survey, which would take around 7-10 mins to complete: forms.cloud.microsoft/e/j2jr9nH3X0 I would really appreciate insights from y'all!

nlp_pranav's tweet image. I'm researching how ACL's peer review policies impact NLP research quality, career trajectories, and inclusivity within our community. I am running a survey, which would take around 7-10 mins to complete: forms.cloud.microsoft/e/j2jr9nH3X0 

I would really appreciate insights from y'all!

Pranav reposted
ShouldHaveCat's tweet image.

paper accepted but cannot go to the location, sigh


spent some money on coffee recently and i am a happy little caffeinated boy now.

nlp_pranav's tweet image. spent some money on coffee recently and i am a happy little caffeinated boy now.

Pranav reposted

If you are applying to NLP PhDs, considering working with Abhilasha!!

Life update: I’m excited to share that I’ll be starting as faculty at the Max Planck Institute for Software Systems(@mpi_sws_) this Fall!🎉 I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year: lasharavichander.github.io/contact.html

lasha_nlp's tweet image. Life update: I’m excited to share that I’ll be starting as faculty at the Max Planck Institute for Software Systems(@mpi_sws_) this Fall!🎉

I’ll be recruiting PhD students in the upcoming cycle, as well as research interns throughout the year:   lasharavichander.github.io/contact.html


Pranav reposted

“I’ve been told by my producer not to do an impression of a peacock”


Pranav reposted

🚨 Calling all NLP researchers! WiNLP 2025 is seeking mentors for our pre-submission program 💫 Help early-career authors & underrepresented voices improve their work. 🗓️ Assignments: June 27 🗓️ Feedback due: July 11 Interested? Reply to join! #WiNLP #Mentorship #EMNLP2025

WiNLPWorkshop's tweet image. 🚨 Calling all NLP researchers!

WiNLP 2025 is seeking mentors for our pre-submission program 💫

Help early-career authors & underrepresented voices improve their work.
🗓️ Assignments: June 27
🗓️ Feedback due: July 11

Interested? Reply to join!

#WiNLP #Mentorship #EMNLP2025

Pranav reposted

🖋️ Curious how writing differs across (research) cultures? 🚩 Tired of “cultural” evals that don't consult people? We engaged with researchers to identify & measure ✨cultural norms✨in scientific writing, and show that❗LLMs flatten them❗ 📜 arxiv.org/abs/2506.00784 1/11

shaily99's tweet image. 🖋️ Curious how writing differs across (research) cultures?
🚩 Tired of “cultural” evals that don't consult people?

We engaged with researchers to identify & measure ✨cultural norms✨in scientific writing, and show that❗LLMs flatten them❗

📜 arxiv.org/abs/2506.00784 

1/11

why the fuck did i try to rewrite my entire codebase in vllm, one week before emnlp deadline? anyways, I can finally process all my experiments within 30 mins as compared to 72 hours on huggingface.


Pranav reposted

Super honored to win the Language Modeling SAC award! I'll be presenting this work Wednesday in the 2pm poster session in Hall 3-- would love to chat with folks there or at the rest of the conference about long context data, ICL, inference time methods, New Mexican food, etc :)

In-context learning provides an LLM with a few examples to improve accuracy. But with long-context LLMs, we can now use *thousands* of examples in-context. We find that this long-context ICL paradigm is surprisingly effective– and differs in behavior from short-context ICL! 🧵

abertsch72's tweet image. In-context learning provides an LLM with a few examples to improve accuracy. But with long-context LLMs, we can now use *thousands* of examples in-context.

We find that this long-context ICL paradigm is surprisingly effective– and differs in behavior from short-context ICL!  🧵


these difficult times have called for doing emergency reviewing for ACL at a chole bhature stand.


Pranav reposted

X has been shoving political ads down my throat for the right-wing Afd in the days prior to the election. Such selective micro-targeting is disgusting & dangerous for the young! Tempted to finally be done with this platform, but I’m worried about all opposing voices leaving 😥


Pranav reposted

UW’s @TechPolicyLab and I invite applications for a 2-year Postdoctoral Researcher position in "AI Alignment with Ethical Principles" focusing on language technologies, societal impact, and tech policy. Kindly share! apply.interfolio.com/162834 Priority review deadline: 3/28/2025


Pranav reposted

Hi followers, from today onwards, we will be posting our group announcements over at the other place! Follow us there for our group updates.

DS_research_HH's tweet image. Hi followers, from today onwards, we will be posting our group announcements over at the other place! Follow us there for our group updates.

Pranav reposted

My @NSF grant researching global LGBTQ+ organizations amidst political repression was ordered to shut down 🙃


Happy Chinese New year everyone! 恭喜发财!

nlp_pranav's tweet image. Happy Chinese New year everyone! 恭喜发财!

Pranav reposted

Some happy news: my dissertation on "Coherent Physical Commonsense Reasoning in Foundational Language Models" is finally available online! 🎓deepblue.lib.umich.edu/handle/2027.42…


Loading...

Something went wrong.


Something went wrong.