Tencent-Hunyuan

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

HY-Embodied: Embodied Foundation Models for Real-World Agents

HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

From Vision-Language-Action Models to a Real-World Robot Learning Stack

Official code for HiLS-Attention

Official Implementation of SAGE-GRPO:Manifold-Aware Exploration for Reinforcement Learning in Video Generation

RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination

Research artifacts from Hyra (/ˈhaɪ.rɑː/)

Implementation of GradLoc from the Tencent Hunyuan blog "Stabilizing RLVR via Token-level Gradient Diagnosis and Layerwise Clipping".

HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents

[SIGGRAPH2026] Official code for SIGGRAPH2026 paper: R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

[ICML 2026] Twins: Learn to Predict Unified Representations with Focal Loss

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

Open-source native multimodal pretraining — without catastrophic forgetting.

Benchmark for repository-level code understanding: 500 open-ended questions from real GitHub Discussions across 50 repositories, graded by a checklist-based verification protocol (ASE 2026)