Modals for complete video perception understanding
👋 Open to Work
Subhansh Malviya
Subh775
AI & ML interests
Computer Vision | Perception Understanding | Semantic Segmentation
Recent Activity
upvoted a collection 5 days ago
Llama 3.1 Collection liked a Space 5 days ago
barunsaha/slide-deck-ai liked a model 9 days ago
openai/gpt-oss-120bOrganizations
Stage 1: In-The-wild Instance Segmentation
Threat Detection models
Versatile trained weights with accurate inferencing responses
Modals for complete video perception understanding
Challenging datasets and trained weights for multi-class, fine-grained vehicle, lane, & object detection
Stage 1: In-The-wild Instance Segmentation
training data and model checkpoints for SD ControlNet based Image generation model
Threat Detection models
Curated Demographic Facial Datasets
Versatile trained weights with accurate inferencing responses
High-impact models and datasets crafted for Transformers and LLMs