Yogesh
@yogeshpaul.bsky.social
Software Engineer + graduate student at Georgia Tech CS, specializing in Machine learning.
Reposted by Yogesh
Optimized HDBSCAN clustering for reconstructing the merger history of the Milky Way: applications and limitations. Andrea Sante et. al. https://arxiv.org/abs/2509.09839
September 15, 2025 at 9:38 AM
Optimized HDBSCAN clustering for reconstructing the merger history of the Milky Way: applications and limitations. Andrea Sante et. al. https://arxiv.org/abs/2509.09839
Reposted by Yogesh
Here's a neat thing: You can use machine-learning analyses to understand how large language models work.
Learn how here:
mikexcohen.substack.com/s/ml-on-llms
Learn how here:
mikexcohen.substack.com/s/ml-on-llms
Dissecting LLMs with ML | Mike X Cohen | Substack
Understand how large language models (LLMs) really work by applying machine learning (ML) methods to their internal activations. Each post explores how LLMs process text, isolate patterns, and generat...
mikexcohen.substack.com
September 4, 2025 at 4:37 AM
Here's a neat thing: You can use machine-learning analyses to understand how large language models work.
Learn how here:
mikexcohen.substack.com/s/ml-on-llms
Learn how here:
mikexcohen.substack.com/s/ml-on-llms
Reposted by Yogesh
According to NASA/ADS this paper has now garnered more than 1,000 citations!
astro.theoj.org/article/1112...
astro.theoj.org/article/1112...
Importance Nested Sampling and the MultiNest Algorithm | Published in The Open Journal of Astrophysics
By Farhan Feroz, Michael P. Hobson & 2 more. A discussion of importance nested sampling and an introduction to the MultiNest algorithm, with applications to astrophysics.
astro.theoj.org
April 7, 2025 at 9:48 AM
According to NASA/ADS this paper has now garnered more than 1,000 citations!
astro.theoj.org/article/1112...
astro.theoj.org/article/1112...
Reposted by Yogesh
Y’all gotta go read books. There’s no way around it.
Read books.
Form your own opinions.
LEARN THINGS.
READ BOOKS WHILE LIBRARIES ARE STILL AROUND
Read books.
Form your own opinions.
LEARN THINGS.
READ BOOKS WHILE LIBRARIES ARE STILL AROUND
April 5, 2025 at 2:29 AM
Y’all gotta go read books. There’s no way around it.
Read books.
Form your own opinions.
LEARN THINGS.
READ BOOKS WHILE LIBRARIES ARE STILL AROUND
Read books.
Form your own opinions.
LEARN THINGS.
READ BOOKS WHILE LIBRARIES ARE STILL AROUND
Reposted by Yogesh
Galaxy Morphology Classification via Deep Semi-Supervised Learning with Limited Labeled Data
https://arxiv.org/pdf/2504.00500
Zhijian Luo, Jianzhen Chen, Zhu Chen, Shaohua Zhang, Liping Fu, Hubing Xiao, Chenggang Shu.
https://arxiv.org/pdf/2504.00500
Zhijian Luo, Jianzhen Chen, Zhu Chen, Shaohua Zhang, Liping Fu, Hubing Xiao, Chenggang Shu.
https://arxiv.org/abs/2504.00500
arXiv abstract link
arxiv.org
April 2, 2025 at 6:26 AM
Galaxy Morphology Classification via Deep Semi-Supervised Learning with Limited Labeled Data
https://arxiv.org/pdf/2504.00500
Zhijian Luo, Jianzhen Chen, Zhu Chen, Shaohua Zhang, Liping Fu, Hubing Xiao, Chenggang Shu.
https://arxiv.org/pdf/2504.00500
Zhijian Luo, Jianzhen Chen, Zhu Chen, Shaohua Zhang, Liping Fu, Hubing Xiao, Chenggang Shu.
Reposted by Yogesh
Coded Llama 3.2 model from scratch and shared it on the HF Hub.
Why? Because I think 1B & 3B models are great for experimentation, and I wanted to share a clean, readable implementation for learning and research: huggingface.co/rasbt/llama-...
Why? Because I think 1B & 3B models are great for experimentation, and I wanted to share a clean, readable implementation for learning and research: huggingface.co/rasbt/llama-...
March 31, 2025 at 5:13 PM
Coded Llama 3.2 model from scratch and shared it on the HF Hub.
Why? Because I think 1B & 3B models are great for experimentation, and I wanted to share a clean, readable implementation for learning and research: huggingface.co/rasbt/llama-...
Why? Because I think 1B & 3B models are great for experimentation, and I wanted to share a clean, readable implementation for learning and research: huggingface.co/rasbt/llama-...
Reposted by Yogesh
dolphin: A fully automated forward modeling pipeline powered by artificial intelligence for galaxy-scale strong lenses
https://arxiv.org/pdf/2503.22657
Anowar J. Shajib, Nafis Sadik Nihal, Chin Yi Tan, Vedant Sahu, Simon Birrer, Tommaso Treu, Joshua Frieman.
https://arxiv.org/pdf/2503.22657
Anowar J. Shajib, Nafis Sadik Nihal, Chin Yi Tan, Vedant Sahu, Simon Birrer, Tommaso Treu, Joshua Frieman.
https://arxiv.org/abs/2503.22657
arXiv abstract link
arxiv.org
March 31, 2025 at 4:31 AM
dolphin: A fully automated forward modeling pipeline powered by artificial intelligence for galaxy-scale strong lenses
https://arxiv.org/pdf/2503.22657
Anowar J. Shajib, Nafis Sadik Nihal, Chin Yi Tan, Vedant Sahu, Simon Birrer, Tommaso Treu, Joshua Frieman.
https://arxiv.org/pdf/2503.22657
Anowar J. Shajib, Nafis Sadik Nihal, Chin Yi Tan, Vedant Sahu, Simon Birrer, Tommaso Treu, Joshua Frieman.
Reposted by Yogesh
Just to share a bit of academic content… have you heard of VoRA? arxiv.org/abs/2503.20680 🙃
Vision as LoRA
We introduce Vision as LoRA (VoRA), a novel paradigm for transforming an LLM into an MLLM. Unlike prevalent MLLM architectures that rely on external vision modules for vision encoding, VoRA internaliz...
arxiv.org
March 27, 2025 at 6:25 PM
Just to share a bit of academic content… have you heard of VoRA? arxiv.org/abs/2503.20680 🙃
Reposted by Yogesh
Classification of Radio Sources Through Self-Supervised Learning
https://arxiv.org/pdf/2503.19111
Nicolas Baron Perez, Marcus Brüggen, Gregor Kasieczka, Luisa Lucie-Smith.
https://arxiv.org/pdf/2503.19111
Nicolas Baron Perez, Marcus Brüggen, Gregor Kasieczka, Luisa Lucie-Smith.
https://arxiv.org/abs/2503.19111
arXiv abstract link
arxiv.org
March 26, 2025 at 9:00 AM
Classification of Radio Sources Through Self-Supervised Learning
https://arxiv.org/pdf/2503.19111
Nicolas Baron Perez, Marcus Brüggen, Gregor Kasieczka, Luisa Lucie-Smith.
https://arxiv.org/pdf/2503.19111
Nicolas Baron Perez, Marcus Brüggen, Gregor Kasieczka, Luisa Lucie-Smith.
Reposted by Yogesh
Generative AI for Validating Physics Laws
https://arxiv.org/pdf/2503.17894
Maria Nareklishvili, Nicholas Polson, Vadim Sokolov.
https://arxiv.org/pdf/2503.17894
Maria Nareklishvili, Nicholas Polson, Vadim Sokolov.
https://arxiv.org/abs/2503.17894
arXiv abstract link
arxiv.org
March 25, 2025 at 4:37 AM
Generative AI for Validating Physics Laws
https://arxiv.org/pdf/2503.17894
Maria Nareklishvili, Nicholas Polson, Vadim Sokolov.
https://arxiv.org/pdf/2503.17894
Maria Nareklishvili, Nicholas Polson, Vadim Sokolov.
Reposted by Yogesh
Deep-TAO: The Deep Learning Transient Astronomical Object data set for Astronomical Transient Event Classification
https://arxiv.org/pdf/2503.16714
John F. Suárez-Pérez, Catalina Gómez, Mauricio Neira, Marcela Hernández Hoyos, Pablo Arbeláez, Jaime E. Forero-Romero.
https://arxiv.org/pdf/2503.16714
John F. Suárez-Pérez, Catalina Gómez, Mauricio Neira, Marcela Hernández Hoyos, Pablo Arbeláez, Jaime E. Forero-Romero.
https://arxiv.org/abs/2503.16714
arXiv abstract link
arxiv.org
March 24, 2025 at 4:31 AM
Deep-TAO: The Deep Learning Transient Astronomical Object data set for Astronomical Transient Event Classification
https://arxiv.org/pdf/2503.16714
John F. Suárez-Pérez, Catalina Gómez, Mauricio Neira, Marcela Hernández Hoyos, Pablo Arbeláez, Jaime E. Forero-Romero.
https://arxiv.org/pdf/2503.16714
John F. Suárez-Pérez, Catalina Gómez, Mauricio Neira, Marcela Hernández Hoyos, Pablo Arbeláez, Jaime E. Forero-Romero.
Reposted by Yogesh
Stream Automatic Detection with Convolutional Neural Network (SAD-CNN)
https://arxiv.org/pdf/2503.17202
Alex Vera-Casanova. et al.
https://arxiv.org/pdf/2503.17202
Alex Vera-Casanova. et al.
https://arxiv.org/abs/2503.17202
arXiv abstract link
arxiv.org
March 24, 2025 at 4:31 AM
Stream Automatic Detection with Convolutional Neural Network (SAD-CNN)
https://arxiv.org/pdf/2503.17202
Alex Vera-Casanova. et al.
https://arxiv.org/pdf/2503.17202
Alex Vera-Casanova. et al.
Reposted by Yogesh
Maximum-likelihood regression with systematic errors for astronomy and the physical sciences: II. Hypothesis testing of nested model components for Poisson data
https://arxiv.org/pdf/2503.17335
M. Bonamente, D. Zimmerman, Y. Chen.
https://arxiv.org/pdf/2503.17335
M. Bonamente, D. Zimmerman, Y. Chen.
https://arxiv.org/abs/2503.17335
arXiv abstract link
arxiv.org
March 24, 2025 at 4:31 AM
Maximum-likelihood regression with systematic errors for astronomy and the physical sciences: II. Hypothesis testing of nested model components for Poisson data
https://arxiv.org/pdf/2503.17335
M. Bonamente, D. Zimmerman, Y. Chen.
https://arxiv.org/pdf/2503.17335
M. Bonamente, D. Zimmerman, Y. Chen.
Reposted by Yogesh
My next tutorial on pretraining an LLM from scratch is now out. It starts with a step-by-step walkthrough of understanding, calculating, and optimizing the loss. After training, we update the text generation function with temperature scaling and top-k sampling: www.youtube.com/watch?v=Zar2...
March 23, 2025 at 1:38 PM
My next tutorial on pretraining an LLM from scratch is now out. It starts with a step-by-step walkthrough of understanding, calculating, and optimizing the loss. After training, we update the text generation function with temperature scaling and top-k sampling: www.youtube.com/watch?v=Zar2...
Reposted by Yogesh
A multi-model approach using XAI and anomaly detection to predict asteroid hazards
https://arxiv.org/pdf/2503.15901
Amit Kumar Mondal, Nafisha Aslam, Prasenjit Maji, Hemanta Kumar Mondal.
https://arxiv.org/pdf/2503.15901
Amit Kumar Mondal, Nafisha Aslam, Prasenjit Maji, Hemanta Kumar Mondal.
https://arxiv.org/abs/2503.15901
arXiv abstract link
arxiv.org
March 21, 2025 at 8:42 AM
A multi-model approach using XAI and anomaly detection to predict asteroid hazards
https://arxiv.org/pdf/2503.15901
Amit Kumar Mondal, Nafisha Aslam, Prasenjit Maji, Hemanta Kumar Mondal.
https://arxiv.org/pdf/2503.15901
Amit Kumar Mondal, Nafisha Aslam, Prasenjit Maji, Hemanta Kumar Mondal.
Reposted by Yogesh
Applications of Large Language Model Reasoning in Feature Generation
Read more: https://arxiv.org/html/2503.11989v1
Read more: https://arxiv.org/html/2503.11989v1
March 21, 2025 at 12:42 AM
Applications of Large Language Model Reasoning in Feature Generation
Read more: https://arxiv.org/html/2503.11989v1
Read more: https://arxiv.org/html/2503.11989v1
Reposted by Yogesh
I like this paper: Gruber, C., Schenk, P. O., Schierholz, M., Kreuter, F., & Kauermann, G. (2023). Sources of Uncertainty in Machine Learning-A Statisticians ’ View. arxiv.org/abs/2305.16703. 1/
Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' View
Supervised machine learning and predictive models have achieved an impressive standard today, enabling us to answer questions that were inconceivable a few years ago. Besides these successes, it becom...
arxiv.org
March 20, 2025 at 9:24 PM
I like this paper: Gruber, C., Schenk, P. O., Schierholz, M., Kreuter, F., & Kauermann, G. (2023). Sources of Uncertainty in Machine Learning-A Statisticians ’ View. arxiv.org/abs/2305.16703. 1/
Reposted by Yogesh
Search for dark matter subhalos among unassociated Fermi-LAT sources in presence of dataset shift
https://arxiv.org/pdf/2503.14584
Aurelio Amerio, Dmitry Malyshev, Bryan Zaldivar, Viviana Gammaldi, Miguel Ángel Sánchez-Conde.
https://arxiv.org/pdf/2503.14584
Aurelio Amerio, Dmitry Malyshev, Bryan Zaldivar, Viviana Gammaldi, Miguel Ángel Sánchez-Conde.
https://arxiv.org/abs/2503.14584
arXiv abstract link
arxiv.org
March 20, 2025 at 7:29 AM
Search for dark matter subhalos among unassociated Fermi-LAT sources in presence of dataset shift
https://arxiv.org/pdf/2503.14584
Aurelio Amerio, Dmitry Malyshev, Bryan Zaldivar, Viviana Gammaldi, Miguel Ángel Sánchez-Conde.
https://arxiv.org/pdf/2503.14584
Aurelio Amerio, Dmitry Malyshev, Bryan Zaldivar, Viviana Gammaldi, Miguel Ángel Sánchez-Conde.
Reposted by Yogesh
Data Release 1 of the Dark Energy Spectroscopic Instrument
https://arxiv.org/pdf/2503.14745
DESI Collaboration et al.
https://arxiv.org/pdf/2503.14745
DESI Collaboration et al.
https://arxiv.org/abs/2503.14745
arXiv abstract link
arxiv.org
March 20, 2025 at 7:29 AM
Data Release 1 of the Dark Energy Spectroscopic Instrument
https://arxiv.org/pdf/2503.14745
DESI Collaboration et al.
https://arxiv.org/pdf/2503.14745
DESI Collaboration et al.
Reposted by Yogesh
Analyses of anomalous lensing events detected from the UKIRT microlensing survey
https://arxiv.org/pdf/2503.14789
Cheongho Han et al.
https://arxiv.org/pdf/2503.14789
Cheongho Han et al.
https://arxiv.org/abs/2503.14789
arXiv abstract link
arxiv.org
March 20, 2025 at 7:29 AM
Analyses of anomalous lensing events detected from the UKIRT microlensing survey
https://arxiv.org/pdf/2503.14789
Cheongho Han et al.
https://arxiv.org/pdf/2503.14789
Cheongho Han et al.
Reposted by Yogesh
Euclid Quick Data Release (Q1). The Strong Lensing Discovery Engine E - Ensemble classification of strong gravitational lenses: lessons for Data Release 1
https://arxiv.org/pdf/2503.15328
Euclid Collaboration et al.
https://arxiv.org/pdf/2503.15328
Euclid Collaboration et al.
https://arxiv.org/abs/2503.15328
arXiv abstract link
arxiv.org
March 20, 2025 at 7:30 AM
Euclid Quick Data Release (Q1). The Strong Lensing Discovery Engine E - Ensemble classification of strong gravitational lenses: lessons for Data Release 1
https://arxiv.org/pdf/2503.15328
Euclid Collaboration et al.
https://arxiv.org/pdf/2503.15328
Euclid Collaboration et al.
Reposted by Yogesh
Euclid Quick Data Release (Q1). LEMON - Lens Modelling with Neural networks. Automated and fast modelling of Euclid gravitational lenses with a singular isothermal ellipsoid mass profile
https://arxiv.org/pdf/2503.15329
Euclid Collaboration et al.
https://arxiv.org/pdf/2503.15329
Euclid Collaboration et al.
https://arxiv.org/abs/2503.15329
arXiv abstract link
arxiv.org
March 20, 2025 at 7:30 AM
Euclid Quick Data Release (Q1). LEMON - Lens Modelling with Neural networks. Automated and fast modelling of Euclid gravitational lenses with a singular isothermal ellipsoid mass profile
https://arxiv.org/pdf/2503.15329
Euclid Collaboration et al.
https://arxiv.org/pdf/2503.15329
Euclid Collaboration et al.
Reposted by Yogesh
Searching for strong lensing by late-type galaxies in UNIONS
https://arxiv.org/pdf/2503.10610
J. A. Acevedo Barroso, B. Clément, F. Courbin, R. Gavazzi, C. Lemon, K. Rojas, D. Scott, S. Gwyn, F. Hammer, M. J. Hudson, E. A. Magnier.
https://arxiv.org/pdf/2503.10610
J. A. Acevedo Barroso, B. Clément, F. Courbin, R. Gavazzi, C. Lemon, K. Rojas, D. Scott, S. Gwyn, F. Hammer, M. J. Hudson, E. A. Magnier.
https://arxiv.org/abs/2503.10610
arXiv abstract link
arxiv.org
March 14, 2025 at 7:23 AM
Searching for strong lensing by late-type galaxies in UNIONS
https://arxiv.org/pdf/2503.10610
J. A. Acevedo Barroso, B. Clément, F. Courbin, R. Gavazzi, C. Lemon, K. Rojas, D. Scott, S. Gwyn, F. Hammer, M. J. Hudson, E. A. Magnier.
https://arxiv.org/pdf/2503.10610
J. A. Acevedo Barroso, B. Clément, F. Courbin, R. Gavazzi, C. Lemon, K. Rojas, D. Scott, S. Gwyn, F. Hammer, M. J. Hudson, E. A. Magnier.
Reposted by Yogesh
A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs
Read more: https://arxiv.org/html/2503.05050v1
Read more: https://arxiv.org/html/2503.05050v1
March 16, 2025 at 8:42 AM
A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs
Read more: https://arxiv.org/html/2503.05050v1
Read more: https://arxiv.org/html/2503.05050v1
Reposted by Yogesh
Deep source separation of overlapping gravitational-wave signals and non-stationary noise artifacts
https://arxiv.org/pdf/2503.10398
Niklas Houba.
https://arxiv.org/pdf/2503.10398
Niklas Houba.
https://arxiv.org/abs/2503.10398
arXiv abstract link
arxiv.org
March 14, 2025 at 7:23 AM
Deep source separation of overlapping gravitational-wave signals and non-stationary noise artifacts
https://arxiv.org/pdf/2503.10398
Niklas Houba.
https://arxiv.org/pdf/2503.10398
Niklas Houba.