Ishan Kumar
@ishankumar216MS CS at Columbia | prev Data and Applied Scientist @ Microsoft | Machine Learning Enthusiast | Graduate @iitroorkee
Similar User
@fairuz_shadmani
@drybuffin
@chaoyue_song
@ashpect01
@GodwinHoudji
@DeressaWodajo
If you want to do a PhD with me on Multi-Agent LLMs (see our recent #NeurIPS2024 paper on GovSim arxiv.org/pdf/2404.16698), I highly recommend you apply by *Nov 14* to Cooperative AI PhD Fellowship! Up to $40K/year w/ other benefits. Email me if you want to iterate your proposal.
Excited to introduce our 3 papers at #ACL2024NLP on #Causality, #NLProc & #Music: ➡️Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals ➡️CausalCite: A Causal Formulation of Paper Citations ➡️Moûsai: Efficient Text-to-Music Diffusion Models
IndicGenBench is accepted at ACL'24. Use it via huggingface: huggingface.co/collections/go… @GoogleAI @partha_p_t @nitish_gup @ShikharSSU @dinesh_tewari1
New work on evaluating LLMs for generation in Indic Languages: IndicGenBench 👉5 diverse tasks, 29 Indic languages, >100k examples. 👉Curated using human translations ensuring high quality. 👉Multi-way parallel dataset. arxiv.org/abs/2404.16816 github.com/google-researc… (1/n)
Glad to have cross-institutional collaboration w/ @ishankumar216* @ZhijingJin* @EhsanMokhtarian @syguoML @chenyuen0103 Negar Kiyavash @mrinmayasachan @bschoelkopf at @MPI_IS @eth_en @epfl @Cambridge_Uni & UIUC! 📜 Paper: arxiv.org/abs/2311.02790 💻 Code: github.com/causalNLP/caus…
Unsatisfied with citations as a measure of paper quality? Check out CausalCite, an alternative metric where we quantify paper impact by its causal effect on followup works. We ask the counterfactual question, "Had this paper not existed, what would happen to the followup papers?"
📢New Paper📢 All Citations are equal but some are more impactful than others💡🤔 Checkout our work CausalCite: a causal formulation of Citations!
Unsatisfied with citations as a measure of paper quality? Check out CausalCite, an alternative metric where we quantify paper impact by its causal effect on followup works. We ask the counterfactual question, "Had this paper not existed, what would happen to the followup papers?"
Excited for our paper "Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good (NLP4SG)" at #EMNLP2023 Findings. We propose 3 NLP tasks: (1) detect if a paper relates to NLP4SG , (2) check which UN SDG it addresses, and (3) extract task & methods proposed.
🚨New paper🚨 Contrastively trained Vision-Language Model’s (like CLIP) are poor at compositional reasoning Our new paper improves this: “Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality” arxiv.org/pdf/2305.13812…
#GPT4 saved my dog's life. After my dog got diagnosed with a tick-borne disease, the vet started her on the proper treatment, and despite a serious anemia, her condition seemed to be improving relatively well. After a few days however, things took a turn for the worse 1/
After success with Images, diffusion models are also being used in the text domain now. In this blog, I explore some of the key ideas of papers using Continuous Diffusion Models for NLP. medium.com/@ishankumar216… #NLP #diffusionmodels
pip install scikit-learn It's easy to take for granted, but this single command gives you functionality I'd value at hundreds of thousands of dollars, if not more. Not to mention amazing documentation that beautifully weaves guides and references. Hats off to @scikit_learn
Learnt so much from contributing at Ignite!
Announcing PyTorch-Ignite's v0.4.7 release 🔥 We have a new State Parameter Scheduler, improved loggers, additional features and bug fixes. This time we had many new contributors so thank you to our community for their amazing contributions! Read more: github.com/pytorch/ignite…
Yes! Fitting comfortably on a colab GPU should become a criteria
personally a bit bored by 530 billion parameters models I'd be more interested in a model that can be used or researched by 530 million humans
We are happy to announce that we will be participating in #Hacktoberfest this year! The repositories participating are: 👉 Core Ignite: github.com/pytorch/ignite 👉 Code Generator: github.com/pytorch-ignite… 👉 Examples: github.com/pytorch-ignite…. Everyone is welcome to contribute!
In scikit-learn 1.0, we decided to deprecate the sklearn.datasets.load_boston function because the design of this dataset casually assumes that people prefer to buy housing in racially segregated neighborhoods.
Dive into Deep Learning now supports @PyTorch The first 8 chapters are ready with more on their way. Thanks to DSG IIT Roorkee @dsg_iitr, particularly @gollum_here who adapted the code into PyTorch. More at D2L.ai. @mli65 @smolix @zacharylipton @astonzhangAZ
United States Trends
- 1. #TysonPaul 165 B posts
- 2. Serrano 215 B posts
- 3. #NetflixFight 60,4 B posts
- 4. #netflixcrash 13,7 B posts
- 5. Canelo 8.503 posts
- 6. Rosie Perez 11,9 B posts
- 7. Shaq 13,2 B posts
- 8. #buffering 9.805 posts
- 9. My Netflix 70,6 B posts
- 10. Father Time 9.235 posts
- 11. Tori Kelly 4.407 posts
- 12. ROBBED 89,1 B posts
- 13. Gronk 6.080 posts
- 14. Cedric 18,5 B posts
- 15. #boxing 40,4 B posts
- 16. Ramos 68,2 B posts
- 17. Roy Jones 5.561 posts
- 18. Barrios 49 B posts
- 19. Logan 64,3 B posts
- 20. He's 58 10,7 B posts
Something went wrong.
Something went wrong.