- Published on
Building real-time intent recognition achieving sub-500ms latency with 70% accuracy improvement, and implementing Query AutoComplete using Ghosting approach with N-gram models and fine-tuned GPT-2.
Transformers
All Posts
- computer-vision (3)
transformers (2)
- mlops (2)
- nlp (2)
- machine-learning (2)
- yolov8 (1)
- sam (1)
- fastapi (1)
- airflow (1)
- edge-ai (1)
- tensorrt (1)
- quantization (1)
- model-optimization (1)
- system-design (1)
- content-moderation (1)
- gpt-2 (1)
- production-ml (1)
- deep-learning (1)
- research (1)
- edge-computing (1)
- social-impact (1)
- iit-delhi (1)
- aws (1)
- kubernetes (1)
- mlflow (1)
- sagemaker (1)
- Published on
Reduced weekly construction site reports time by 70% using ML models (YOLOv8, UNet, SAM, Transformers) for materials detection. Built event-driven integration handling 1000+ concurrent jobs.