Building The Next-Gen Boxing Simulator with Procedural Physical Motion and Precise Intuitive Control🥊🎮

⛩️ Tokyo
Joined November 2022
Mr. For Example retweeted
⚡️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: github.com/Tencent-Hunyuan/H… arxiv: arxiv.org/abs/2510.10726
10
108
7
732
67,484
Mr. For Example retweeted
⚡️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: github.com/imlixinyang/Flash… Page: imlixinyang.github.io/FlashW…
18
116
15
747
121,076
Mr. For Example retweeted
HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools like COLMAP, enabling instant 3D application use. ✅Innovative 3D Memory: Introduces a scalable world caching mechanism, ensuring geometric consistency across any camera trajectory. ✅Top-Ranked Performance: #1 on Stanford’s WorldScore, excelling in video generation and 3D reconstruction benchmarks.(huggingface.co/spaces/Howiee…) Built on HunyuanWorld 1.0, Voyager blends video generation with 3D modeling, delivering camera-controlled, high-fidelity RGB-D sequences. Control scenes via keyboard or joystick for unmatched 3D consistency. Explore now: 🌐Project Page: 3d-models.hunyuan.tencent.co… 🔗GitHub:github.com/Tencent-Hunyuan/H… 🤗HuggingFace:huggingface.co/tencent/Hunyu… 📝Technical Details: 3d-models.hunyuan.tencent.co…
53
253
71
1,281
198,545
Those who intuit something is lacking in LLMs struggle to pinpoint the gap beyond inadequate metaphors like “stochastic parrot” or “glorified autocomplete.” What you’re groping for is fractured entangled representation (FER). That’s the concrete crux of your slippery intuitions. It’s why these models can keep improving in dramatic and genuinely nontrivial ways yet still suffer from an underlying sickness. It’s where real opportunity and hope lie for revolutionary progress, Representation is at the heart of thought, of creativity, and indeed of intelligence itself. It is possible to “know” an unfathomable amount and yet still represent it poorly. And it’s possible for representation to be better. And it will ultimately happen one way or another.
40
102
29
863
83,742
Mr. For Example retweeted
🔥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. @TencentHunyuan #HunyuanWorld Try it now:3d.hunyuan.tencent.com/scene… Github:github.com/Tencent-Hunyuan/H……
2
24
2
120
24,212
Mr. For Example retweeted
🧩 PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers 📐 Jupyter Notebook 🥳 Thanks to @kevin_yuchenlin ❤ @lin_chenguo ❤ @paulpanwang ❤ Honglei Yan ❤ Yiqiang Feng ❤ Yadong Mu ❤ Katerina Fragkiadaki ❤ Thanks to @alexandernasa ❤ for the gradio app. 🌐page: wgsxm.github.io/projects/par… 🧬code: github.com/wgsxm/PartCrafter 📄paper: arxiv.org/abs/2506.05573 🍊jupyter: github.com/camenduru/PartCra…
5
18
1
83
4,080
Mr. For Example retweeted
The Era of Experience & The Age of Design Great talk by Richard Sutton: Humans have the ability to take design to the next level, and actually design things that can design (“make AI that can make AI”), taking us from Replicators into “The Age of Design”.
8
35
5
261
28,653
Don't give up.
20
313
9
2,302
70,373
76
3,110
60
30,482
1,457,903
60
7,394
135
35,263
1,257,464
Difference between GPT-4o and o1. 😁
72
422
66
6,726
441,101
39
2,524
58
20,309
1,155,034
Mr. For Example retweeted
Super excited for the new chapter of our journey! We are forming Comfy Org with an insane team: - comfyanonymous: creator of ComfyUI - mcmonkey4eva: creator of SwarmUI - Dr Lt Data: creator of ComfyUI-Manager - pythongosssss: major contributor of ComfyUI - robinken: creator of Comfy Registry - yoland68 (me): creator of ComfyCLI We are a team dedicated to improve ComfyUI and support the ComfyUI ecosystem. Our core mission is to advance and democratize Gen AI tooling! You can follow us at comfy dot org
47
114
22
671
89,808
Mr. For Example retweeted
Elon Musk
@elonmusk10 Apr 2024
Precisely
7,043
32,470
3,063
206,718
51,617,924
Mr. For Example retweeted
Replying to @zhiwen_fan_
@WayneINR generously shared his today's advancements in InstantSplat with me. Another breakthrough: 3 images, no camera poses, no intrinsics, trained in under 20 seconds, and rasterized with gsplat. Check out the video for a sneak peek into the future: instantsplat.github.io/
3
6
48
3,241
Mr. For Example retweeted
Massimo
@Rainmaker19737 Mar 2024
Physical visualization of the least square regression
54
763
110
5,507
914,323
(づ ̄ 3 ̄)づ Workflow File up: - prompt-able 3D asset generation - generation time on 4090 like 15 - 30 sec (dependent on geometry_extract_resolution) \ - circumvents saving bug w/ name templating 👇🏽Link in thread👇🏽 #Nerf #3DModel #3DPrinting #gamedev #animation
8
24
1
156
11,519
Mr. For Example retweeted
Elon Musk
@elonmusk5 Mar 2024
This administration is both importing voters and creating a national security threat from unvetted illegal immigrants. It is highly probable that the groundwork is being laid for something far worse than 9/11. Just a matter of time.
26,985
88,934
8,167
334,065
36,707,472
Mr. For Example retweeted
1/ We’ve submitted a letter to President Biden regarding the AI Executive Order and its potential for restricting open source AI. We believe strongly that open source is the only way to keep software safe and free from monopoly. Please help amplify.
111
874
119
2,648
2,057,273