Sayak Paul
Machine Learning Engineer, Hugging Face | Diffusers & Edge AI Specialist | Google Developer Expert
Verified Proof of Work Artifacts
2 items catalogedEach artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Sayak Paul. Every entry undergoes editorial source verification.
Optimizing Latent Diffusion Models for Edge & Mobile Deployment
Authored comprehensive engineering benchmarks and guides demonstrating INT8 and FP16 quantization, TensorRT compilation, and CoreML conversion for running diffusion pipelines on consumer hardware.
Quantization below 8-bit precision requires calibration against representative prompt distributions to prevent latent vector drift.
Diffusion Model Distillation & Latent Consistency Optimization
Co-authored and integrated Latent Consistency Model (LCM) LoRA adapters into Hugging Face Diffusers, compressing multi-step diffusion sampling into 2 to 4 inference steps for real-time generation.
Aggressive 2-step distillation can introduce subtle high-frequency smoothing in photorealistic background details.