Stars
🤖 curl | sh installer script for Typst
An integrated editor for the typst typesetting system.
Turn Markdown into beautiful PDFs with Tideflow instantly - offline, portable desktop app
Package desktop applications as AppImages that run on common Linux-based operating systems, such as RHEL, CentOS, openSUSE, SLED, Ubuntu, Fedora, debian and derivatives. Join #AppImage on irc.liber…
template for pure Python libraries. As simple as possible. No magic.
The open-source CapCut alternative
Get your documents ready for gen AI
Gymnasium-based benchmarking suite for testing RL algorithms on real-world scenarios
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Repository of the code of the VAEABMIL model for OOD-Aware Multiple Instance Learning.
Democratizing Reinforcement Learning for LLMs
Benchmark for evaluating the generalization capabilities of Multi-Objective Reinforcement Learning (MORL) algorithms.
[AAAI 2024] Mab2Rec: Multi-Armed Bandits Recommender
[IJAIT 2021] MABWiser: Contextual Multi-Armed Bandits Library
🧠 Laws, Theories, Principles and Patterns for developers and technologists.
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
Deep Multiple Instance Learning library for Pytorch
Unified Implementations of Offline Reinforcement Learning Algorithms
Sm: enhanced localization in Multiple Instance Learning for medical imaging classification (NeurIPS 2024)
JAX implementation of WSRL and RL baselines | ICLR 2025
Gymnasium-based interface for continuous control using MELCOR.
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
An RL-Gym for Challenge Problems in Data-Driven Modeling and Control of Fluid Dynamics.
Meta-Reinforcement Learning with Evolving Gradient Regularization
Code and data related to LOVE (Latest Observed Values Encoding), my self-learning emotional framework for machines