SJ
AI & ML interests
Recent Activity
Organizations
-
teknium/dataforge-economics
Viewer β’ Updated β’ 880 β’ 36 β’ 49 -
theblackcat102/evol-codealpaca-v1
Viewer β’ Updated β’ 111k β’ 3.85k β’ 179 -
ise-uiuc/Magicoder-Evol-Instruct-110K
Viewer β’ Updated β’ 111k β’ 5.41k β’ 174 -
andersonbcdefg/synthetic_retrieval_tasks
Viewer β’ Updated β’ 205k β’ 17 β’ 79
-
deepseek-ai/deepseek-coder-6.7b-base
Text Generation β’ 7B β’ Updated β’ 43.5k β’ 123 -
vikhyatk/moondream1
Text Generation β’ 2B β’ Updated β’ 10.2k β’ 487 - RunningFeatured179
Whisper Speech X DreamTalk
π½179Combine voice cloning and portrait lipsync animation
-
FlashTex: Fast Relightable Mesh Texturing with LightControlNet
Paper β’ 2402.13251 β’ Published β’ 14
- Running2.79k
OutfitAnyone
π’2.79kGenerate virtual tryβon images of any person wearing uploaded clothes
- RunningFeatured268
Segment Anything Web
π»268Segment objects in images using clickβbased masks
- Running12
Zero Shot Classification Demo
π’12Classify images without training data using AI
- RunningFeatured1.25k
Whisper Web
π€1.25kTranscribe audio files to text instantly
- Running11k
AI Comic Factory
π©11kCreate your own AI comic with a single prompt
- Running5
Semantic Autocomplete Demo 1
π5Generate text suggestions based on context
- Running98
Segment Anything WebGPU
β‘98Segment objects in images directly in your browser
-
NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation
Paper β’ 2311.12229 β’ Published β’ 25 -
Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
Paper β’ 2312.16171 β’ Published β’ 37 -
DreamDistribution: Prompt Distribution Learning for Text-to-Image Diffusion Models
Paper β’ 2312.14216 β’ Published β’ 12
-
teknium/dataforge-economics
Viewer β’ Updated β’ 880 β’ 36 β’ 49 -
theblackcat102/evol-codealpaca-v1
Viewer β’ Updated β’ 111k β’ 3.85k β’ 179 -
ise-uiuc/Magicoder-Evol-Instruct-110K
Viewer β’ Updated β’ 111k β’ 5.41k β’ 174 -
andersonbcdefg/synthetic_retrieval_tasks
Viewer β’ Updated β’ 205k β’ 17 β’ 79
-
NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation
Paper β’ 2311.12229 β’ Published β’ 25 -
Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
Paper β’ 2312.16171 β’ Published β’ 37 -
DreamDistribution: Prompt Distribution Learning for Text-to-Image Diffusion Models
Paper β’ 2312.14216 β’ Published β’ 12
-
deepseek-ai/deepseek-coder-6.7b-base
Text Generation β’ 7B β’ Updated β’ 43.5k β’ 123 -
vikhyatk/moondream1
Text Generation β’ 2B β’ Updated β’ 10.2k β’ 487 - RunningFeatured179
Whisper Speech X DreamTalk
π½179Combine voice cloning and portrait lipsync animation
-
FlashTex: Fast Relightable Mesh Texturing with LightControlNet
Paper β’ 2402.13251 β’ Published β’ 14
- Running2.79k
OutfitAnyone
π’2.79kGenerate virtual tryβon images of any person wearing uploaded clothes
- RunningFeatured268
Segment Anything Web
π»268Segment objects in images using clickβbased masks
- Running12
Zero Shot Classification Demo
π’12Classify images without training data using AI
- RunningFeatured1.25k
Whisper Web
π€1.25kTranscribe audio files to text instantly
- Running11k
AI Comic Factory
π©11kCreate your own AI comic with a single prompt
- Running5
Semantic Autocomplete Demo 1
π5Generate text suggestions based on context
- Running98
Segment Anything WebGPU
β‘98Segment objects in images directly in your browser