Tengfei Wang's banner

Tengfei Wang

@DylanTFWang • 3,565 subscribers

Leading World Model team @ Tencent Hunyuan，PhD @ HKUST，previously @ Microsoft Research

Shorts

🎮Get a first look at Tencent HY World 1.5 (WorldPlay)! 🎮 Our newest world model with real-time interaction and long-term memory. It’s going *open-source* tomorrow.

🎮Get a first look at Tencent HY World 1.5 (WorldPlay)! 🎮 Our newest world model with real-time interaction and long-term memory. It’s going open-source tomorrow.

114,035 views

🚀 Tencent 𝗛𝗬-𝗪𝗼𝗿𝗹𝗱 𝟮.𝟬 just dropped Text or image → 3D world (3DGS + Mesh). Fully automatic. Video world models let you 𝘄𝗮𝘁𝗰𝗵. We let you 𝗲𝘅𝗽𝗹𝗼𝗿𝗲. #worldmodel #HYWorld

🚀 Tencent 𝗛𝗬-𝗪𝗼𝗿𝗹𝗱 𝟮.𝟬 just dropped Text or image → 3D world (3DGS + Mesh). Fully automatic. Video world models let you 𝘄𝗮𝘁𝗰𝗵. We let you 𝗲𝘅𝗽𝗹𝗼𝗿𝗲. #worldmodel #HYWorld

17,396 views

More cases generated by the open-source version of HY World 1.5. 🐼"A cute panda walking in bamboo forest" code & model:

More cases generated by the open-source version of HY World 1.5. 🐼"A cute panda walking in bamboo forest" code & model:

13,869 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

Genie3 generates videos. We generate 𝟯𝗗 𝘄𝗼𝗿𝗹𝗱𝘀 you can actually use. Launching tomorrow — Tencent #HYWorld 2.0, an engine-ready World Model🚀 This isn't a video. It's a real 3D scene, all generated & editable. One image in. A whole 3D world out. 🔥Open-source tomorrow

542,256 views • 1 month ago

⚡️Generating 3DGS scenes in 5 seconds on a single GPU⚡️ #FlashWorld enables ⚡️*fast*⚡️ (10~100x faster than previous methods) and 🔥*high-quality*🔥 3D world generation, from a single image or text prompt. Code: Page:

⚡️Generating 3DGS scenes in 5 seconds on a single GPU⚡️ #FlashWorld enables ⚡️fast⚡️ (10~100x faster than previous methods) and 🔥high-quality🔥 3D world generation, from a single image or text prompt. Code: Page:

119,877 views • 7 months ago

⚡️Your video → a 3D scene. Just in seconds.⚡️ Only *one* model. No more steps❌. Just results🔝. #WorldMirror reconstructs everything (3DGS, depth, cameras) from any inputs (image, video, 3D prior) *all-at-once*! code: arxiv:

⚡️Your video → a 3D scene. Just in seconds.⚡️ Only one model. No more steps❌. Just results🔝. #WorldMirror reconstructs everything (3DGS, depth, cameras) from any inputs (image, video, 3D prior) all-at-once! code: arxiv:

66,847 views • 7 months ago

📽️➡️🏠 Can an image become a consistent 3D world? Video Diffusion Models look stunning, but 3D consistency is still a nightmare… #WorldStereo is different. We gave the AI a "3D brain" using Geometric Memories. The result? ✅ Zero flickering. ✅ Perfect 3D consistency.

📽️➡️🏠 Can an image become a consistent 3D world? Video Diffusion Models look stunning, but 3D consistency is still a nightmare… #WorldStereo is different. We gave the AI a "3D brain" using Geometric Memories. The result? ✅ Zero flickering. ✅ Perfect 3D consistency.

19,865 views • 3 months ago

Autoregressive diffusion models drift for long videos? 📉 We fixed it.🚀 Speed + Stability = ✅ Meeting *Test-Time Correction (TTC)*. We stop error accumulation in its tracks without any retraining. ✅ Training-free ✅ 1 minute+ stable generation ✅ Negligible overhead

Autoregressive diffusion models drift for long videos? 📉 We fixed it.🚀 Speed + Stability = ✅ Meeting Test-Time Correction (TTC). We stop error accumulation in its tracks without any retraining. ✅ Training-free ✅ 1 minute+ stable generation ✅ Negligible overhead

16,460 views • 2 months ago

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to *many * components. paper: code:

🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to many components. paper: code:

27,013 views • 5 months ago

⚡️Training RL on world models used to be a headache. Not anymore. ⚡️ Meet *WorldCompass*, a major update to *HY World 1.5*: 🏃‍♂️ Fast rollouts 🏗️ stable train ✨ Higher quality paper: code: page:

⚡️Training RL on world models used to be a headache. Not anymore. ⚡️ Meet WorldCompass, a major update to HY World 1.5: 🏃‍♂️ Fast rollouts 🏗️ stable train ✨ Higher quality paper: code: page:

15,269 views • 3 months ago

🔥A standout feature of HunyuanWorld: its AI-generated 3D scenes are fully editable. (screen recording of our GUI) ⚡️Join our waitlist now. will open a few quotas daily. Tencent HY #HunyuanWorld Try it now： Github：

🔥A standout feature of HunyuanWorld: its AI-generated 3D scenes are fully editable. (screen recording of our GUI) ⚡️Join our waitlist now. will open a few quotas daily. Tencent HY #HunyuanWorld Try it now： Github：

24,088 views • 10 months ago

No more content to load