Pinned Repositories
advantage-alignment
AI_Project_CSP
bioinformatics
my bioinformatics adventures
bioinformatics_project
CP-Flow
Convex potential flows
DataAnalysis
These are the solution to assignments which we were given in data analysis course in Sharif University Of Technology which was taught by Dr. Ehyaee and Dr. Mirsadeghi from math department.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
loqa
LOQA: Learning with Opponent Q-learning Awareness (ICLR-2024)
McMedHacksGrandChallenge
The winner project for AlphaTau Grand Challenge in McMedHacks (https://mcmedhacks.com/hackathon/).
miladink.github.io
MiladInk's Repositories
MiladInk/loqa
LOQA: Learning with Opponent Q-learning Awareness (ICLR-2024)
MiladInk/McMedHacksGrandChallenge
The winner project for AlphaTau Grand Challenge in McMedHacks (https://mcmedhacks.com/hackathon/).
MiladInk/AI_Project_CSP
MiladInk/bioinformatics
my bioinformatics adventures
MiladInk/bioinformatics_project
MiladInk/CP-Flow
Convex potential flows
MiladInk/DataAnalysis
These are the solution to assignments which we were given in data analysis course in Sharif University Of Technology which was taught by Dr. Ehyaee and Dr. Mirsadeghi from math department.
MiladInk/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
MiladInk/flax
Flax is a neural network library for JAX that is designed for flexibility.
MiladInk/InvariantRiskMinimization
PyTorch code to run synthetic experiments.
MiladInk/miladink.github.io
MiladInk/learnxor
XOR function is important to the community of machine learning for historical reasons. The field was set on hold as people found out with a single layer network even XOR function cannot be learned. However, with slightly deeper networks and a little non-linearity, we are able to learn XOR. in this repo, we want to make sure that it is the case.
MiladInk/LOLA
my experiments with the Lola(learning with opponent learning awareness)
MiladInk/meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
MiladInk/MNIST-GAN
It is the first GAN I have trained on the MNIST dataset with PyTorch
MiladInk/model-free-opponent-shaping
Code for Model-Free Opponent Shaping (ICML 2022)
MiladInk/Modern-Information-Retrival
MiladInk/pytorch-glow
Pytorch Implementation of OpenAI's GLOW
MiladInk/rethinkmarl
Rethinking Multi Agent Reinforcement Learning in the Era of Agentic Large Language Models - ICLR 2025 workshop
MiladInk/Science4Cast-SanatiesFinest
MiladInk/sdeflow-light
A minimalist implementation of score-based diffusion model
MiladInk/SSLCG
MiladInk/stable-diffusion-webui
Stable Diffusion web UI
MiladInk/test-sglang
test repo for testing and playing with sglang
MiladInk/theImageGrid
MiladInk/weight_init
I have tried to reproduce the presentation Andrej Karpathy has made in cs1231n video lectures trying to describe the importance of the weight initialization