Fast, modular reference implementation and easy training of Semantic Segmentation algorithms in PyTorch.
Repository Index
47,133 repositories indexed
49–72 of 76 · Most stars
Library for Fast and Flexible Human Pose Estimation
- tensorlayer
- tensorflow
- openpose
- pose-estimation
Official Repository for the Uni-Mol Series Methods
- molecular-modeling
- pre-trained-model
- pretraining
- deep-learning
A Theano framework for building and training neural networks
allRank is a framework for training learning-to-rank neural models based on PyTorch.
- learning-to-rank
- ndcg
- ranking
- information-retrieval
vibe coded supermimic within 1h, LAFAN passed within 1.5 gpuh training
A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.
- python
- machine-learning
- random-forest
- tensorflow
Skill training with a corruption and reconstruction loop: train an agent's skill library, not its weights.
🚧 Under construction — no-training RefMod reference adapters for MiniMax H3 (compress reference images/videos into tiny latents, no training needed).
- comfyui
- comfyui-custom-node
- comfyui-extension
- comfyui-manager
A Python native dynamical system simulation framework in the block diagram paradigm.
- blockdiagram
- control-systems
- hierarchical-modeling
- nonlinear-dynamics
Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.
- embodied-agent
- game-agent
- game-ai
- mihoyo
Speedrun for pretraining without backpropagation
Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.
- artificial-intelligence
- clip
- pathology
- vision-and-language
[arXiv 2026] Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling
- audio-to-video
- joint-audio-video-generation
- unified-model
- video-to-audio
[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"
- diffusion-transformers
- eccv2026
- image-generation
- training-free
INGInious is a secure and automated exercises assessment platform using your own tests, also providing a pluggable interface with your existing LMS.
- grading
- assessment
- education
- e-assessment
TranslatedTreat agents as functions, and write ideas as programs. Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.
Feather agent harness, training integrations, and evaluation tools for knowledge work
An autonomous agent that profiles, optimizes, and validates AI training code.
Trading environnement for RL agents, backtesting and training.
- trading
- backtesting
- reinforcement-learning-agent
- reinforcement-learning
Transformer-SRU LiDAR navigation for Unitree G1: Isaac Lab training, MuJoCo validation, and ROS 2 deployment.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation
- biological-images
- root
- painter
- segmentation
Docker image gathering packers and tools for making datasets of packed executables and training machine learning models for packing detection
- docker-image
- executable-packing
- malware-packers
- research-platform