Orpheus Morpheus
📚
3
Generate unique similar compositions to any MIDI
Jack Voide
Mindweller
AI & ML interests
None yet
Recent Activity
liked a Space about 4 hours ago
projectlosangeles/Orpheus-Morpheus liked a model about 4 hours ago
JANGQ-AI/Kimi-K2.6-Small-JANGTQ liked a model about 4 hours ago
TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-GGUFOrganizations
None yet
liked a
Space about 4 hours ago
liked 4
models about 4 hours ago
JANGQ-AI/Kimi-K2.6-Small-JANGTQ
Text Generation • 39B • Updated • 863 • 2
TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-GGUF
27B • Updated • 4.36k • 7
anthfu/supergemma4-26b-uncensored-gguf-v2
Text Generation • 25B • Updated • 22.8k • 101
Jackrong/Qwopus-GLM-18B-Merged-GGUF
Text Generation • 16B • Updated • 75.8k • 216
liked 6
models 3 days ago
UnstableLlama/Qwen3.6-27B-exl3-6.00bpw
11B • Updated • 43 • 2
FINAL-Bench/Darwin-9B-NEG
Text Generation • 10B • Updated • 760 • 35
deepseek-ai/DeepSeek-V4-Pro
Text Generation • 862B • Updated • 123k • • 2.91k
z-lab/Qwen3.6-27B-DFlash
Text Generation • 2B • Updated • 3.45k • 118
Jackrong/Qwopus3.6-27B-v1-preview
Image-Text-to-Text • 28B • Updated • 1.44k • 28
UnstableLlama/Qwen3.6-27B-exl3-4.15bpw
9B • Updated • 117 • 5
liked a
model 5 days ago
liked a
model 11 days ago
liked 2
Spaces 11 days ago
reacted to kelsend's post with 👍 11 days ago
Post
2632
Tencent Open-Sources Hunyuan 3D World Model 2.0 Generate Editable 3D Game Worlds with One Sentence, Compatible with Unity/UE
Tencent has officially released and open-sourced Hunyuan 3D World Model 2.0 (HY-World 2.0), enabling AI to evolve from video generation to creating playable, editable 3D world
Core Highlights
Text / Image / Video → Directly generate exportable 3D assets (Mesh / 3DGS / Point Cloud)
Seamlessly integrates with Unity / Unreal Engine for game maps and level prototyping
One-click reconstruction of digital twin scenes from single images/videos, no camera parameters required
Spatial Agent for intelligent navigation trajectories no wall penetration, consistent spatial height
All-new HY-Pano-2.0 + WorldMirror 2.0 architecture, achieving SOTA in 3D reconstruction and novel view synthesis
Key Breakthrough
Unlike Genie 3 and Hunyuan 1.5, which only output videos, HY-World 2.0 generates re-editable 3D worlds that support collision, interaction, and engine import
Application Scenarios
Game Development, Indoor Preview, Urban Planning, Digitalization of Cultural Heritage, Embodied AI Simulation
Tencent has officially released and open-sourced Hunyuan 3D World Model 2.0 (HY-World 2.0), enabling AI to evolve from video generation to creating playable, editable 3D world
Core Highlights
Text / Image / Video → Directly generate exportable 3D assets (Mesh / 3DGS / Point Cloud)
Seamlessly integrates with Unity / Unreal Engine for game maps and level prototyping
One-click reconstruction of digital twin scenes from single images/videos, no camera parameters required
Spatial Agent for intelligent navigation trajectories no wall penetration, consistent spatial height
All-new HY-Pano-2.0 + WorldMirror 2.0 architecture, achieving SOTA in 3D reconstruction and novel view synthesis
Key Breakthrough
Unlike Genie 3 and Hunyuan 1.5, which only output videos, HY-World 2.0 generates re-editable 3D worlds that support collision, interaction, and engine import
Application Scenarios
Game Development, Indoor Preview, Urban Planning, Digitalization of Cultural Heritage, Embodied AI Simulation
liked 2
models 11 days ago
liked a
model 13 days ago
reacted to omarkamali's post with 👍 14 days ago
Post
4533
We got Qwen 3.5 to count Rs in Strawberry correctly! 🚨
Building on Sawtone, we’ve been testing a different way to feed language into an LLM to build the next generation of multilingual AI.
The usual setup gives the model tokenized text and asks it to perform various linguistic tasks. That works surprisingly well, until it doesn’t. Accents disappear. Words get mangled. Internal structure gets blurred away. And the cost of that gets higher once you move into multilingual and lower-resource settings.
So we tried adding a second path.
In addition to the normal text input, the model also receives Sawtone: a byte-level word representation that preserves how a word is written, how it sounds, and how it is structured.
Same LLM. Better interface.
In this proof of concept with Qwen 3.5 0.8B, that pushed our eval from 64% to 88%. The gains showed up exactly where tokenized models usually get shaky: diacritics, character order, exact spelling, and other form-sensitive behavior.
Sawtone itself is tokenizer-free, byte-level, and pre-trained across 507 languages.
Still early, but promising!
Building on Sawtone, we’ve been testing a different way to feed language into an LLM to build the next generation of multilingual AI.
The usual setup gives the model tokenized text and asks it to perform various linguistic tasks. That works surprisingly well, until it doesn’t. Accents disappear. Words get mangled. Internal structure gets blurred away. And the cost of that gets higher once you move into multilingual and lower-resource settings.
So we tried adding a second path.
In addition to the normal text input, the model also receives Sawtone: a byte-level word representation that preserves how a word is written, how it sounds, and how it is structured.
Same LLM. Better interface.
In this proof of concept with Qwen 3.5 0.8B, that pushed our eval from 64% to 88%. The gains showed up exactly where tokenized models usually get shaky: diacritics, character order, exact spelling, and other form-sensitive behavior.
Sawtone itself is tokenizer-free, byte-level, and pre-trained across 507 languages.
Still early, but promising!
- 5 replies