Tags
#AI
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
Getting started with ML and AI
As the “About” section of this repo shows, I am an astrophysicist working on high-energy astronomical transients in radio wavelengths. My journey into ML and AI started when I r...
#Astrophysics
Getting started with ML and AI
As the “About” section of this repo shows, I am an astrophysicist working on high-energy astronomical transients in radio wavelengths. My journey into ML and AI started when I r...
#Bayesian Analysis
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
#Behavioral Analysis
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
#FSP
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
#GPT-oss
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
#Interpretability
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
#LLMs
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
#LSTM
RNNs, LSTMs, and the classification of astronomical transients
This project focuses on classifying light curves of astronomical transients using recurrent neural networks.
#Llama3
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
#ML
RNNs, LSTMs, and the classification of astronomical transients
This project focuses on classifying light curves of astronomical transients using recurrent neural networks.
Getting started with ML and AI
As the “About” section of this repo shows, I am an astrophysicist working on high-energy astronomical transients in radio wavelengths. My journey into ML and AI started when I r...
#Qwen3
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
#RNN
RNNs, LSTMs, and the classification of astronomical transients
This project focuses on classifying light curves of astronomical transients using recurrent neural networks.
#SN
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
RNNs, LSTMs, and the classification of astronomical transients
This project focuses on classifying light curves of astronomical transients using recurrent neural networks.
#TDE
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
Bayesian-like Processes In LLMs - Few-Shot Prompting And The Prior Gap
Bayes’ theorem is probably one of my favorite ideas in statistics. The idea that we update our beliefs based on observed data sits at the core of the scientific method (and shou...
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
RNNs, LSTMs, and the classification of astronomical transients
This project focuses on classifying light curves of astronomical transients using recurrent neural networks.
#Time-series
Mechanistic Interpretability via Layer Patching in a Time-Series Analysis
In the previous posts, I looked at the way GPT-oss classifies astronomical light curves, and especially at the tension between two pieces of information: the timescale of the tr...
Benchmarking And Behavioral Study of LLMs For Time-Series Analysis
In my previous post I used an LSTM to classify astronomical transients. The motivation for this project is laid out in detail there, however there is one point I want to reitera...
RNNs, LSTMs, and the classification of astronomical transients
This project focuses on classifying light curves of astronomical transients using recurrent neural networks.