Vishvak Murahari

NLP + ML Ph.D. candidate @princeton_nlp
Ex. @Google @allen_ai @Microsoft

[Devansh Bhardwaj @devansh0502]

[1/4]
Vibe Analyst: the future of data science.
No dashboards. No SQL. Just vibe with your data.

Powered by Agent Context Protocols (ACPs) — the first protocol for building multi-agent reasoning systems.

https://t.co/DjP2ypUJZw
Paper: https://t.co/ENXmhWg33k

[Vinay Samuel @vsamuel2003]

PersonaGym – the first platform to evaluate persona agents.

Persona agents are critical to magical AI experiences, but how do we evaluate them?

PersonaGym uses dynamic LLM-powered environments for faithful and targeted agent eval.

https://t.co/keDTeou2o8

[Ameet Deshpande @AmeetDeshpande_]

Our EACL workshop on personalization of Generative AI is accepting ARR submissions.

Deadline: Jan 27th, 2024
Submission form: https://t.co/jlFT9QxazD

The workshop will be co-located with EACL in Malta.
Workshop date: March 21st or March 22nd

Website: https://t.co/oRr6T517PN

[Pranjal Aggarwal ✈️ ICLR'26 @PranjalAggarw16]

With LLM based Search Engines like Bard & Perplexity rising, how can creators like NYT maintain ownership & visibility? 🤔

We introduce Generative Engine Optimization (GEO)🔍⚙️- a black-box optimization framework for creators in new-era search!

🔗: https://t.co/WW2I9pCSCv

🧵

[Vishvak Murahari @VishvakM]

Given popular demand, we have decided to extend the deadline to January 10, 2024!

[Ameet Deshpande @AmeetDeshpande_]

We're organizing a workshop on personalization of Gen-AI at Malta.
Submit and attend to immerse in the first principled town-square for conversations surrounding your favorite topics.
Website: https://t.co/tIurnluQbC
Submission: https://t.co/b3cZSixttS

[Vishvak Murahari @VishvakM]

Navigating the dynamic landscape of algorithmic, efficiency, and safety challenges in Gen-AI personalization is key. Join us as our workshop sparks principled discussions and fosters collaboration among industry leaders, academics, startups, and policymakers. Save the date! 🗓️🚀

[Ameet Deshpande @AmeetDeshpande_]

We're organizing a workshop on personalization of Gen-AI at Malta.
Submit and attend to immerse in the first principled town-square for conversations surrounding your favorite topics.
Website: https://t.co/tIurnluQbC
Submission: https://t.co/b3cZSixttS

[Vishvak Murahari @VishvakM]

Thanks to my wonderful collaborators: @AmeetDeshpande_, Peter Clark, Tanmay Rajpurohit, Ashish Sabharwal, @karthik_r_n, @ashwinkalyan7

Website: https://t.co/vnIlshimOe
Code: https://t.co/Ukmllz3nkb
Demo: https://t.co/ECn8POF7Am

[Vishvak Murahari @VishvakM]

QualEval – your LLM data scientist🥼
Quantitative metrics don’t aid in model improvement
Our philosophy – Quality over quantity✅
QualEval qualitatively analyzes tons of data🔍, reasons over mistakes⚠️, and improves your model
Your model dev copilot✈️
Demo:https://t.co/y0EDvjiLV5

[Vishvak Murahari @VishvakM]

QualEval’s insights can be leveraged toward model improvement, enabling unprecedented agility in model iteration. QualEval aids practitioners to accurately discover and precisely improve underperforming sub-domains and sub-tasks, increasing overall performance significantly.📷

[Vishvak Murahari @VishvakM]

I am excited to share that #PrincetonInnovation has featured our innovations around Data Multiplexing, a novel neural network efficiency paradigm, alongside other cutting-edge research from @Princeton this year.

[Dan Friedman @danfriedman0]

Learning Transformer Programs

We designed a modified Transformer that can be trained to solve a task and then automatically converted into a discrete, human-readable program. With @_awettig and @danqi_chen.

Paper: https://t.co/P9PPGaM7Uw
Code: https://t.co/10jYnSdq9N

[1/12]

[Ameet Deshpande @AmeetDeshpande_]

Glad to see the direct impact of our research on OpenAI.

Th recent call for democratic inputs recognizes studying the effects of personalization on model behavior as a key direction.

Link to our work which showed adverse effects of assigning a persona: https://t.co/x784x2zHuc

[Ameet Deshpande @AmeetDeshpande_]

Semantic textual similarity is an important task in NLP.
But sentence similarity can be ambiguous and depends on the aspect of interest.
We propose Conditional-STS, which resolves this ambiguity through conditions.
Even SOTA models find it challenging!
📜https://t.co/MeRyTl2LnZ

[Machine Learning at Georgia Tech @mlatgt]

Congrats to #ICLR2023 Best Paper Awardees @arimorcos, @DhruvBatraDB , and @erikwijmans, pictured on May 1 in Kilagi. Wijmans presented the work at a special award ceremony. @iclr_conf awarded only 4 best papers. (Coauthors not pictured: Manolis Savva, @irrfaan, and @stefmlee)

[Ameet Deshpande @AmeetDeshpande_]

"Extremely" happy to share that our work which pushes the boundaries of extreme classification has been accepted at ICML 2023.
We show that semantic information can be smartly leveraged to improve classification over millions of labels, a pertinent real-world scenario.

[Rama Vedantam @rama_vedantam]

🔥 🔥 Our alternative to CLIP that captures visual-semantic hierarchies 🥳, is more efficient for smaller embeddings ✅, has geometric insights for multimodal learning 🤝🔥🔥

.. led by @kdexd (ex-intern, FAIR)

[Ai2 @allen_ai]

"Depending on the persona assigned to ChatGPT, its toxicity can increase up to [6 times]. This may be ... harmful to an unsuspecting user." @thomasgermain reports on new work from AI2 student researcher @AmeetDeshpande_ & team: https://t.co/XCqF6Ko1Ux

[Princeton Computer Science @PrincetonCS]

New research from @AmeetDeshpande_, @VishvakM and @karthik_r_n featured in @TechCrunch.

Giving ChatGPT a certain "persona" can make it speak like a "bad person," or even Mao Zedong.

The responses, researchers found, can become consistently toxic.

https://t.co/vDEmmhVaHu

[DeepAI @DeepAI]

Lowkey goated when #NaturalLanguageProcessing is the vibe! 🤩 Check out this dope paper by @VishvakM and co. to learn more: https://t.co/EnDmdgFzl9