Tencent-Hunyuan
@tencent-hunyuan • Open source projects from tencent-hunyuan. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
42%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
30 repos
Visible snapshot
21 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (25), Unknown (3), C (1)
Average size
402
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-09-14(5d ago)GitHub API fallback30 repositories
42%
of the visible star count comes from this organization's top three repositories.
402
stars per repository in this same snapshot.
Python
is the most common language here, with 21 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 30 repositories.
Balanced portfolio across 30 reposTop 3 share 42%
Organization pages work best when you separate portfolio breadth from flagship concentration. In Tencent-Hunyuan's case, the visible top three repositories account for about 42% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (25), Unknown (3), C (1). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | tencent-hunyuan/HY-World-2.0 HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds | Python | 2.7K |
| 2 | tencent-hunyuan/Hunyuan3D-WorldClaw WorldClaw: Agentic 3D Open-world Generation at Scale | 1.3K | |
| 3 | tencent-hunyuan/AuK AuK: An Open-Source Foundational Model for Speech Generation and Editing | Python | 1.1K |
| 4 | tencent-hunyuan/UniRL UniRL is a Framework for Unified Multimodal Model Reinforcement Learning | Python | 970 |
| 5 | tencent-hunyuan/HY-Embodied HY-Embodied: Embodied Foundation Models for Real-World Agents | Python | 871 |
| 6 | tencent-hunyuan/OmniWeaving Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning | Python | 810 |
| 7 | tencent-hunyuan/HY-SOAR HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models | Python | 746 |
| 8 | tencent-hunyuan/Hy3 Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency. | Python | 659 |
| 9 | tencent-hunyuan/Hy-MT2 | Python | 635 |
| 10 | tencent-hunyuan/Hy3-preview Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency | Python | 479 |
| 11 | tencent-hunyuan/Hy4-preview | Python | 380 |
| 12 | tencent-hunyuan/Hy-Embodied-0.5-VLA From Vision-Language-Action Models to a Real-World Robot Learning Stack | Python | 301 |
| 13 | tencent-hunyuan/Hunyuan3D-Buffalo1.0 [Tech Report] A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing | 249 | |
| 14 | tencent-hunyuan/Hyra-results Research artifacts from Hyra (/ˈhaɪ.rɑː/) | Python | 156 |
| 15 | tencent-hunyuan/HiLS-Attention Official code for HiLS-Attention | Python | 148 |
| 16 | tencent-hunyuan/Hy-Embodied-RxBrain-1.0 RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination | Python | 130 |
| 17 | tencent-hunyuan/GEAR | Python | 68 |
| 18 | tencent-hunyuan/HY-Embodied-0.5-X HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents | Python | 67 |
| 19 | tencent-hunyuan/R-DMesh [SIGGRAPH2026] Official code for SIGGRAPH2026 paper: R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow | Python | 60 |
| 20 | tencent-hunyuan/Simple-Attention-Sparsification Code for our resarch paper "SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking" | Python | 59 |
| 21 | tencent-hunyuan/Twins [ICML 2026] Twins: Learn to Predict Unified Representations with Focal Loss | Python | 37 |
| 22 | tencent-hunyuan/Hy-Embodied-RoboFusion | C | 35 |
| 23 | tencent-hunyuan/UniCom | Python | 34 |
| 24 | tencent-hunyuan/DisCa DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching | Python | 26 |
| 25 | tencent-hunyuan/PlanningBench | 25 | |
| 26 | tencent-hunyuan/Precise | Python | 16 |
| 27 | tencent-hunyuan/RepoProbe 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) | Python | 12 |
| 28 | tencent-hunyuan/Rosetta-inference Open-source native multimodal pretraining — without catastrophic forgetting. | Python | 9 |
| 29 | tencent-hunyuan/evolve-scaler Github page for paper "EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language Rendering" | HTML | 3 |
| 30 | tencent-hunyuan/VisualNeedle A benchmark for active visual search in high-information-density scenes | Python | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.