Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Fast and memory-efficient exact attention

Mamba SSM architecture

Awesome work on hand pose estimation/tracking

Structured state space sequence models

Mastering Diverse Domains through World Models

Skeleton-based Action Recognition

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

Greek Dataset Production from PDF+

Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.

Notes of state-of-the-arts Papers on Hand-Human Pose & Shape Estimation

This repository provides a Python translation of the undistortFunctions that are part of the Scaramuzza's OCamCalib for fisheye cameras. It contains sample code for comparing this Toolbox to the bu…