GitHub

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer

This repository contains the official PyTorch implementation for the ECCV2024 paper "AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer". AdaLog adapts the ...
IEEE

Spiking U-Net++: A Quantization-Adaptive Rate Encoding Based Spike Image Segmentation Framework

Abstract: This paper presents Spiking U-Net++, a novel framework for converting artificial neural networks (ANNs) to spiking neural networks (SNNs) with complex skip connections. We address three key ...
Orlando Sentinel

Science on Tap Beer Festival returns to OSC for fifth year

Toast science with a glass full of it at the fifth Science on Tap Beer Festival, returning to Loch Haven Park on from 1-4 p.m. Saturday (Jan. 24). Orlando Science Center’s family-friendly fundraiser ...
IEEE

Learnable Non-Uniform Quantization With Sampling-Based Optimization for Variable-Rate Learned Image Compression

Abstract: Variable-rate coding is challenging but indispensable for learned image compression (LIC) that is in nature characterized by nonlinear transform coding (NTC). Existing methods for ...
cryptopolitan

Tesla’s AI team creates a patent that addresses AI “drift” in positional encoding

Tesla’s AI team has created a patent for a power-sipping 8-bit hardware that normally handles only simple, rounded numbers to perform elite 32-bit rotations. Tesla slashes the compute power budget to ...
GitHub

Latent Diffusion Models for Unconditional Image Generation

This project provides a complete pipeline for latent diffusion models, covering image dataset encoding into latents, training three different models with two distinct noise schedules, and sampling ...