Alibaba's new open source Qwen3.5-Medium models offer Sonnet 4.5 performance on local computers

This leap is made possible by near-lossless accuracy under 4-bit weight and KV cache quantization, allowing developers to process massive datasets without server-grade infrastructure.
Scientific Research Publishing

Finite Propagation and the Regime Structure of Reality

Jr., T. (2026) Finite Propagation and the Regime Structure of Reality — Classicality and Geometry as Constraint-Limited Phenomena. Open Journal of Philosophy, 16, 138-150. doi: ...
IEEE

Integrated Encoding and Quantization to Enhance Quanvolutional Neural Networks

Abstract: Image processing is one of the most promising applications for quantum machine learning. Quanvolutional neural networks with nontrainable parameters are the preferred solution to run on ...
GitHub

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

[2025.09.25]: 🔥🔥🔥 We released a toolkit that tests the impact of numerical precision and enables deterministic LLM inference. This helps eliminate the training–inference mismatch in reinforcement ...
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 ...