Stars
Official Implementation of EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL
Real-time, interactive spatial audio generation for videos and world models.
Fast, concurrent inference for YuE2. Same model and recipe: 1.68× faster per song, 3.31× more songs per GPU.
Cuti Harness: An open-source, plugin-based video world harness
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
AuK: An Open-Source Foundational Model for Speech Generation and Editing
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation
Official implementation for paper "Fourier is Frontier: Frequency-Aware Autoencoding for High-Fidelity Music Reconstruction". We treat is as a new decoder for Music Reconstruction.
🪐 HelixWorld: real-time interactive audio-visual world model.
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.
Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.
🚀 Fastest Anything-to-Audio Gen for conditioned sound and music creation.
Official implementation of the CVPR 2026 paper "SonoWorld: From One Image to a 3D Audio-Visual Scene."
Official Implementation of SAGE-GRPO:Manifold-Aware Exploration for Reinforcement Learning in Video Generation
[ICLR 2026] A two-stage evaluation benchmark for Text-to-Audio generation, assessing category, count, ordering, and timestamp accuracy with Gemini 2.5 Pro.
Allow your 🦞 bot to Shout, Speak, with "human" vibe
A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…
Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
ICML 2024 "From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation"