Vladimir B retweetledi
Vladimir B
6.8K posts
Vladimir B retweetledi
We’re open-sourcing HY-World 2.0, a multimodal world model that generates, reconstructs, and simulates interactive *3D worlds* from text, images, and videos.
Outputs can be integrated into game engines and embodied simulation pipelines.
Key highlights:
🔹 One-click world generation
Turn text or image into interactive 3D worlds automatically.
🔹 Pipeline-ready 3D outputs
Editable 3D worlds for Unity and Unreal Engine, with standard 3D exports including mesh, 3DGS, and point clouds.
🔹 Unified world model system
One model family for world generation and reconstruction across synthetic and real-world scenes.
🔹 Interactive character mode
Explore generated 3D worlds in real time with physics-aware movement and collision support.
✨ Apply for access: 3d.hunyuan.tencent.com/sceneTo3D
🔗 GitHub: github.com/Tencent-Hunyua…
🤗 Hugging Face: huggingface.co/tencent/HY-Wor…
📄 Technical Report: 3d-models.hunyuan.tencent.com/world/world2_0…
English
Vladimir B retweetledi
Vladimir B retweetledi
Ожившая "Всадница" К. Брюллова.
Есть ляпы, конечно ИИшные, но в целом нравится. Пусть будет))
Русский
Vladimir B retweetledi
⚡️ 12 апреля – День космонавтики. Ровно 65 лет назад с космодрома Байконур стартовал космический корабль «Восток» с лётчиком-космонавтом Юрием Гагариным
🚀 Это был первый в мире полёт человека в космос
🔗 t.me/RusEmbassyMins…
#Гагарин65 #НавсегдаПервый #ДеньКосмонавтики2026
Русский
Vladimir B retweetledi
🙏 Χριστός Ανέστη! Ευχόμαστε σε όλους σας Καλό Πάσχα και Καλή Ανάσταση!
Христос Воскресе! Желаем всем вам счастливой Пасхи!
Vladimir B retweetledi
#FirstInSpace
👨🚀 On April 12, 1961, 6️⃣5️⃣ years ago, Soviet cosmonaut Yuri #Gagarin became the First man to venture into space!
🚀 #Vostok1 soared to 327 km, orbited Earth at 28'260 km/h & safely returned — 106 historic minutes that changed the world forever.
#Gagarin1961
English
Vladimir B retweetledi
Vladimir B retweetledi
🚀 Today marks 6️⃣5️⃣ years since humanity ventured into space – a historic feat accomplished by our cosmonaut, an outstanding Soviet citizen, Yuri #Gagarin.
The 1️⃣0️⃣6️⃣ minutes of Yuri Gagarin’s flight changed the course of world history.
👉 Learn more: t.me/MFARussia/29169
English
Vladimir B retweetledi
Vladimir B retweetledi
Vladimir B retweetledi
Qwen3.5-35B-A3B-GGUF is now the #3 trending model on Hugging Face!
Run it locally on 22GB RAM: huggingface.co/unsloth/Qwen3.…
English
Vladimir B retweetledi
Qwen releases 4 new Qwen3.5 Small models!
Qwen3.5: 0.8B • 2B • 4B • 9B
Run Qwen3.5-0.8B, 2B and 4B on your phone. Run 9B on 6GB RAM.
The vision reasoning LLMs perform better than models 4x their size.
GGUFs: huggingface.co/collections/un…
Guide: unsloth.ai/docs/models/qw…
Qwen@Alibaba_Qwen
🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast, great for edge device • 4B → a surprisingly strong multimodal base for lightweight agents • 9B → compact, but already closing the gap with much larger models And yes — we’re also releasing the Base models as well. We hope this better supports research, experimentation, and real-world industrial innovation. Hugging Face: huggingface.co/collections/Qw… ModelScope: modelscope.cn/collections/Qw…
English
Vladimir B retweetledi
Introducing Jan-Code-4B 💻
A compact coding model tuned for practical day-to-day tasks. Generation, refactors, debugging, tests — all runnable locally in Jan.
Download Jan: jan.ai
Model: huggingface.co/collections/ja…
English
Vladimir B retweetledi
Hello, creators and builders,
After a joyful Chinese New Year break, we’re back with one of our most exciting releases yet.
Here’s the new era for Qwen: Qwen3.5, a full-stack family of models that sees further improvements in reasoning, multimodality, and efficiency.
Let’s dive in.
English
Vladimir B retweetledi
Ubuntu 26.04 LTS ends a 40 year old sudo tradition – and some folks aren't happy. omgubuntu.co.uk/2026/02/ubuntu…
English
Vladimir B retweetledi
New Model:
huihui-ai/Huihui-Qwen3.5-27B-abliterated
This is an uncensored version of Qwen/Qwen3.5-27B created with abliteration
huggingface.co/huihui-ai/Huih…
Suomi
Vladimir B retweetledi
@Minister_Prawdy Само сочетание слов "поляки и Бандера" несовместимое. Для русских Бандера тоже является большим злом. Странно. что кто-то его называет "героем" (это антигерой).
Русский
Jeśli jesteś w Polsce anty-banderowcem, to będziesz ścigany przez polską prokuraturę informują banderowcy z ukrainy. Polska już coraz bardziej przypomina Głupią Brytanię.
ukrleakseng.substack.com/p/go-to-jail-i…
Polski
Vladimir B retweetledi
1/3 Qwen3.5 Open-Source Family Expands 🚀
More intelligence, less compute. Introducing the Medium Model Series: Qwen3.5-Flash, Qwen3.5-35B-A3B, Qwen3.5-122B-A10B, Qwen3.5-27B
Qwen3.5-35B-A3B: Surpasses the previous Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B. Proof that architecture, data quality, and RL move intelligence forward—not just parameter counts.
Qwen3.5-122B & 27B: Narrowing the gap with frontier models in complex agent scenarios.
Qwen3.5-Flash (Hosted): 1M context length + official built-in tools.
Build with more efficiency.
English