StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.
Qkd: Quantization- aware knowledge distillation
3 Pith papers cite this work, alongside 47 external citations. Polarity classification is still indexing.
3
Pith papers citing it
47
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Diffusion-generated, distribution-matched synthetic images enable zero-shot quantized object detectors to outperform prior zero-shot methods and even real-data QAT at 4-bit and 3-bit precision.
A few-thousand-parameter quantized U-Net-style model, trained with quantization-aware distillation, is claimed to segment terrain well enough for ESP32-S3 deployment via a Rust TinyML compiler.
citing papers explorer
-
Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks
StoMPP progressively binarizes BNN layers layerwise from input to output via stochastic masks, delivering depth-scalable accuracy gains in a fully STE-free regime by controlling activation-induced gradient blockades.
-
Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models
Diffusion-generated, distribution-matched synthetic images enable zero-shot quantized object detectors to outperform prior zero-shot methods and even real-data QAT at 4-bit and 3-bit precision.
-
Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation
A few-thousand-parameter quantized U-Net-style model, trained with quantization-aware distillation, is claimed to segment terrain well enough for ESP32-S3 deployment via a Rust TinyML compiler.