Shridhar

@JupyterAI

PhD student in ML/NLP @eth_en | Past: @MSFTResearch @AIatMeta @AmazonScience @rptu_kl_ld | He/him. Views are my own.

Science & Technology

san francisco

kumar-shridhar.github.io

Joined August 2017

593Posts 759Followers 1KFollowing

You might like

@shrutirij

@shaily99

@ZhijingJin

@wangchunshu

@rajammanabrolu

@afra_amini

@palu_ema

@AliceBizeul

@mrinmayasachan

@niklas_stoehr

@OpedalAndreas

@cheeesio

@swarnaNLP

@eleanorjiang630

@karstanczak

Pinned

Shridhar

@JupyterAI

Nov 15, 2023

Can Large Language Models (LLMs) accurately judge their own generative output? Introducing ART: Ask, Refine, and Trust. 1. ASK important questions to decide if refinement is needed 2. execute REFINEMENT 3. affirm or withhold TRUST in refinement

Aran Komatsuzaki

@arankomatsuzaki

Nov 15, 2023

The ART of LLM Refinement: Ask, Refine, and Trust Achieves a performance gain of 5 points over self-refinement baselines, while using a much smaller model as the decision maker arxiv.org/abs/2311.07961

arankomatsuzaki's tweet image. The ART of LLM Refinement: Ask, Refine, and Trust

Achieves a performance gain of 5 points over self-refinement baselines, while using a much smaller model as the decision maker

arxiv.org/abs/2311.07961

Shridhar

@JupyterAI

May 20

A student should confidently exploit what it knows and then explore its limits with a teacher. “Learning is often a mix of confidence and curiosity” Check out how we can balance the two for knowledge distillation at @aclmeeting in Vienna! #ACL2025

Shivam Adarsh

@shivamadarsh99

May 20

I am happy to share that our work SIKeD has been accepted to ACL 2025 @aclmeeting findings! More details below

Shridhar

@JupyterAI

May 16

“Reasoning’s like dominoes—nudge that first piece just right and the rest fall perfectly into place.” See you all in Vienna!! #ACL2025

Kushal

@kushalj001

May 16

Happy to share that this paper has now been accepted to ACL 2025 @aclmeeting findings! Paper link: arxiv.org/abs/2311.07945 Details in🧵

Shridhar

@JupyterAI

Apr 16

Gave a simple image to @OpenAI O3 to look into and it zoomed in and out to make sure it’s “q” and not “9”. Is zooming in and out with corresponding text part of some alignment strategy? Or some form of augmentation that works ? Any papers in this direction ?

Shridhar

@JupyterAI

Apr 14

Thought #OpenAI's deep research would add URLs to BibTeX entries easily. Seemed like a perfect use case given I provide all the sources to look into. But NO, it decided to choose a couple of the entries and ignored all the others.

Shridhar

@JupyterAI

Apr 13

Game the system!

Casper Hansen

@casper_hansen_

Apr 13

Llama 4 quietly dropped from 1417 to 1273 ELO, on par with DeepSeek v2.5

Shridhar

@JupyterAI

Apr 7

Claude 3.7 Max Thinking in Cursor is hands down the best for cloning anything 💻✨

Deedy

@deedydas

Apr 7

Claude 3.7 Max Thinking is still the best model for Cursor. — Better at creating apps, refactoring and adding features — Better at figuring out connections between classes — Main benefit of Gemini 2.5 is the 1M context

deedydas's tweet image. Claude 3.7 Max Thinking is still the best model for Cursor.

— Better at creating apps, refactoring and adding features
— Better at figuring out connections between classes
— Main benefit of Gemini 2.5 is the 1M context

Shridhar

@JupyterAI

Apr 6

It’s crazy how the definition of small models is changing so fast. Now it’s 17B MoE with over 100B parameters. Not sure if this will help the open source community to train their own models which was the main reason why llama was so popular.

Ahmad Al-Dahle

@Ahmad_Al_Dahle

Apr 5

Introducing our first set of Llama 4 models! We’ve been hard at work doing a complete re-design of the Llama series. I’m so excited to share it with the world today and mark another major milestone for the Llama herd as we release the *first* open source models in the Llama 4…

Ahmad_Al_Dahle's tweet image. Introducing our first set of Llama 4 models!

We’ve been hard at work doing a complete re-design of the Llama series. I’m so excited to share it with the world today and mark another major milestone for the Llama herd as we release the *first* open source models in the Llama 4…

Shridhar reposted

hardmaru

@hardmaru

Apr 6

😅

Shridhar

@JupyterAI

Apr 6

What’s the equivalent of Vibe coding for AI agent? Anything specific people are testing?

Shridhar reposted

Tongtian Zhu@Neurips 25 SD

@Tongtian_Zhu

Apr 3

ICML 2025's rebuttal process be like🤣: 👨‍💻 Authors: spend a whole week writing a careful rebuttal ✅ Reviewer: clicks "acknowledge" without reading 🚫 Author: not allowed to reply anymore So what does acknowledge mean here? "You speak. I pretend to listen. Conversation over."🙃

Shridhar reposted

Garry Kasparov

@Kasparov63

Dec 12

My congratulations to @DGukesh on his victory today. He has summitted the highest peak of all: making his mother happy!

Shridhar reposted

Aravind Srinivas

@AravSrinivas

Dec 8, 2024

If @narendramodi ji is interested, I would be down to figuring out an economic structure where all Indian students, faculty and researchers can get Perplexity Pro.

Niko McCarty.

@NikoMcCarty

Dec 2, 2024

Indian gov't is buying a subscription to 13,000 academic journals, and then making them all available to "18 million students, faculty, and researchers" for free. The cost is $715 million over 3 years. It includes Elsevier, Nature, and AAAS. Have any other countries done this?