#
Starred repositories
Reliable, minimal and scalable library for evaluate and conduct world model research
Reliable, minimal and scalable library for pretraining foundation and world models
The AI Agent That Lives On Your Desktop And Uses It Like You Do!
JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"
p-doom / jasmine
Forked from FLAIROx/jafarA simple, performant and scalable JAX-based world modeling codebase
[ICCV 2023] Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
Enjoy the magic of Diffusion models!
MiniMax-M2, a model built for Max coding & agentic workflows.
L4P -- a feed-forward foundational model designed for multiple low-level 4D vision perception tasks.
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
Salesforce Enterprise Deep Research
[EMNLP 2025 Oral] Official codebase for Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Discrete Wavelet Transform as a Facilitator for Expressive Latent Space Representation in Variational Autoencoders in Satellite Imagery
Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
Fast and Universal 3D reconstruction model for versatile tasks
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Just another reasonably minimal repo for class-conditional training of pixel-space diffusion transformers.
Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)
NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.