-
CIVOS: Emergence or Recitation?
π48Do LLM agents discover, or recite memorized history?
-
Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation
Paper β’ 2607.26646 β’ Published -
GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly
Paper β’ 2608.17389 β’ Published
Robin L. M. Cheung, MBA PRO
AI & ML interests
Recent Activity
Organizations
-
jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
Text Generation β’ 8B β’ Updated β’ 101 β’ 5 - RunningFeatured215
Janus Pro WebGPU
π215In-browser unified multimodal understanding and generation.
-
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper β’ 2501.08313 β’ Published β’ 304 -
DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF
Text Generation β’ 18B β’ Updated β’ 37.7k β’ 659
- Running on ZeroAgents53
Depth Pro In Meters
π53Generate a 3D model from an image
-
tencent/Hunyuan3D-2
Image-to-3D β’ Updated β’ 156k β’ 1.85k -
Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
Paper β’ 2411.02293 β’ Published β’ 4 - Running on ZeroAgentsFeatured2.7k
Qwen Image Multiple Angles 3D Camera
π₯2.7kEdit image perspective by adjusting camera angle
- PausedAgents1.03k
Whisper Turbo
π€―1.03kTranscribe audio or YouTube videos into text
- Runtime errorAgents4
Pdf2audio
π4Transform text into engaging podcast dialogue
- Build errorAgentsFeatured1.09k
Open NotebookLM
π1.09kPersonalised Podcasts For All - Available in 13 Languages
- PausedAgents853
Video Dubbing (SoniTranslate)
π853Video Dubbing with Open Source Projects
- PausedAgents37
Good Upscaler
π37Enhance image resolution to 16 megapixels
- Running on ZeroAgentsFeatured1.01k
Tile Upscaler
π1.01kUpscale and enhance images with AI-powered tile control
- Runtime errorAgentsFeatured132
Text Guided Flux Inpainting
π132 - Running on ZeroAgents1.7k
Flux.1-dev Upscaler
π1.7kUpscale lowβresolution images to highβresolution versions
- Runtime errorAgents166
Image To Video Cog
π166Generate a video from an image and text prompt
-
genmo/mochi-1-preview
Text-to-Video β’ 10B β’ Updated β’ 3.96k β’ β’ 1.38k - Running on ZeroAgentsFeatured658
Video Background Removal
π½658Remove/Change background of video.
- PausedAgentsFeatured66
Allegro t2v
π66Apache Licensed Advanced Video Generation Model
- PausedAgents37
Good Upscaler
π37Enhance image resolution to 16 megapixels
- Running on ZeroAgentsFeatured1.01k
Tile Upscaler
π1.01kUpscale and enhance images with AI-powered tile control
- PausedAgents67
Flux.1-dev Upscaler
π67Upscale an image by 4x using FLUX
- Running on ZeroAgents1.7k
Flux.1-dev Upscaler
π1.7kUpscale lowβresolution images to highβresolution versions
- Running on ZeroAgentsFeatured328
LGM
π¦328Generate a 3D model and rotating video from text or image
- Build error4
Gaussian Splatting Kit
π¨4 - RunningFeatured58
Gsplat Editor
π58Edit and export 3D splat/PLY point cloud scenes
-
Visual Geometry Grounded Deep Structure From Motion
Paper β’ 2312.04563 β’ Published
- Running333
PolaroidVL Installer
β333install PolaroidVL Model locally on your devices
- Running1
Whisper Timestamped
π1In-browser speech recognition w/ word-level timestamps
- PausedAgentsFeatured255
TTS x Hallo Talking Portrait
π255Generate Talking avatars from Text-to-Speech
- Running on ZeroAgentsFeatured164
LongWriter
π¬164LLM for long context
- PausedFeatured48
CIVOS: Emergence or Recitation?
π48Do LLM agents discover, or recite memorized history?
-
Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation
Paper β’ 2607.26646 β’ Published -
GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly
Paper β’ 2608.17389 β’ Published
-
jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
Text Generation β’ 8B β’ Updated β’ 101 β’ 5 - RunningFeatured215
Janus Pro WebGPU
π215In-browser unified multimodal understanding and generation.
-
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper β’ 2501.08313 β’ Published β’ 304 -
DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF
Text Generation β’ 18B β’ Updated β’ 37.7k β’ 659
- PausedAgents37
Good Upscaler
π37Enhance image resolution to 16 megapixels
- Running on ZeroAgentsFeatured1.01k
Tile Upscaler
π1.01kUpscale and enhance images with AI-powered tile control
- Runtime errorAgentsFeatured132
Text Guided Flux Inpainting
π132 - Running on ZeroAgents1.7k
Flux.1-dev Upscaler
π1.7kUpscale lowβresolution images to highβresolution versions
- Running on ZeroAgents53
Depth Pro In Meters
π53Generate a 3D model from an image
-
tencent/Hunyuan3D-2
Image-to-3D β’ Updated β’ 156k β’ 1.85k -
Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation
Paper β’ 2411.02293 β’ Published β’ 4 - Running on ZeroAgentsFeatured2.7k
Qwen Image Multiple Angles 3D Camera
π₯2.7kEdit image perspective by adjusting camera angle
- Runtime errorAgents166
Image To Video Cog
π166Generate a video from an image and text prompt
-
genmo/mochi-1-preview
Text-to-Video β’ 10B β’ Updated β’ 3.96k β’ β’ 1.38k - Running on ZeroAgentsFeatured658
Video Background Removal
π½658Remove/Change background of video.
- PausedAgentsFeatured66
Allegro t2v
π66Apache Licensed Advanced Video Generation Model
- PausedAgents37
Good Upscaler
π37Enhance image resolution to 16 megapixels
- Running on ZeroAgentsFeatured1.01k
Tile Upscaler
π1.01kUpscale and enhance images with AI-powered tile control
- PausedAgents67
Flux.1-dev Upscaler
π67Upscale an image by 4x using FLUX
- Running on ZeroAgents1.7k
Flux.1-dev Upscaler
π1.7kUpscale lowβresolution images to highβresolution versions
- PausedAgents1.03k
Whisper Turbo
π€―1.03kTranscribe audio or YouTube videos into text
- Runtime errorAgents4
Pdf2audio
π4Transform text into engaging podcast dialogue
- Build errorAgentsFeatured1.09k
Open NotebookLM
π1.09kPersonalised Podcasts For All - Available in 13 Languages
- PausedAgents853
Video Dubbing (SoniTranslate)
π853Video Dubbing with Open Source Projects
- Running on ZeroAgentsFeatured328
LGM
π¦328Generate a 3D model and rotating video from text or image
- Build error4
Gaussian Splatting Kit
π¨4 - RunningFeatured58
Gsplat Editor
π58Edit and export 3D splat/PLY point cloud scenes
-
Visual Geometry Grounded Deep Structure From Motion
Paper β’ 2312.04563 β’ Published
- Running333
PolaroidVL Installer
β333install PolaroidVL Model locally on your devices
- Running1
Whisper Timestamped
π1In-browser speech recognition w/ word-level timestamps
- PausedAgentsFeatured255
TTS x Hallo Talking Portrait
π255Generate Talking avatars from Text-to-Speech
- Running on ZeroAgentsFeatured164
LongWriter
π¬164LLM for long context