Starred repositories
Repo for "Adaptation of Agentic AI"
Data and sample evaluation codes for Multimodal Rewardbench 2
GELab: GUI Exploration Lab. One of the best GUI agent solutions in the galaxy, built by the StepFun-GELab team and powered by Step’s research capabilities.
Towards Scalable Pre-training of Visual Tokenizers for Generation
Official PyTorch Implementation of "SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model Without Variational Autoencoder".
PersonaLive! : Expressive Portrait Image Animation for Live Streaming
V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
54
Updated Dec 15, 2025
Official Implementation of Dynamic erf (Derf).
📷 UCPE: Unified Camera Positional Encoding for Controlled Video Generation
General purpose 3D and 2D game engine using Go (golang) and Vulkan with built in editor
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
🍑 relsim: Relational Visual Similarity | pip install relsim 🌍
Orbax provides common checkpointing and persistence utilities for JAX users
InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models