[arXiv 2026] Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling
- audio-to-video
- joint-audio-video-generation
- unified-model
- video-to-audio
47,133 repositories indexed
121–144 of 156 · Most stars
[arXiv 2026] Unified Audio-Video Creation via Progressive Training and Asymmetric Scheduling
Seamless long-form MiniMax H3 video generation for ComfyUI with native AV latent continuity, chunked sampling, session resume, and Spectrum/Sage/Sol compatibility.
[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models"
[Tech Report] Simplifying and Improving On-Policy Distillation for Few-step Diffusion
TranslatedBring the Codex imagegen workflow and prompt library to any agent; supports one-command installation with npm/pnpm, a companion skill, a standalone API, and a Qwen-Image compatible gateway.
The Complete Street Rule for ArcGIS CityEngine is a scenario oriented design tool intended to enable users to quickly create procedurally generated multimodal streets.
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a platform for autonomous architecture research.
Statistical NLG for spoken dialogue systems
Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
Implementation of the paper -> https://arxiv.org/abs/1709.00155. For converting information present in the form of structured data into natural language text
An automatic code generator for nonlinear model predictive control (NMPC) and the continuation/GMRES method (C/GMRES) based numerical solvers for NMPC
CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
Batched NVIDIA MotionBricks: generate the motion of hundreds of characters in one model call.
ComfyUI custom node: one-click character reference sheet (character card) generation, auto slice & recomposition for Qwen-Image 2.1
Auto-QChem is an automated workflow for the generation and storage of DFT calculations for organic molecules.
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
A CLI tool to automatically add type annotations into Python code. Must have tool for annotating existing code.
An NLP library for Uralic languages such as Finnish, Skolt Sami, Moksha and so on. Also supporting some non-Uralic languages such as Spanish, French, Arabic, Swedish, Norwegian, Russian and English. LLMs, FSTs and More!
Synthetic Adversarial Log Objects: A Framework for synthentic log generation
Realistic synthetic events for testing, demos, and pipelines — streamed live or generated in bulk
Docker image gathering packers and tools for making datasets of packed executables and training machine learning models for packing detection
Natural language generation language
Cryptographic Dataset Generation & Modelling Framework