📦 Model Compression - all666666all · Scour

Knowledge Distillation for Visual Autoregressive Models

⚙️AutoML Academic

Shrinking a Neural Network Often Makes It Smarter

💬Prompt Engineering

siliconopera.com·

A generalist biomedical vision-language model via multi-CLIP knowledge distillation

💬Prompt Engineering Academic

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

⚙️AutoML News Blog

blog.google··Hacker News

The latest Gemma 4 models use a training trick to slash their on-device memory footprint

💬Prompt Engineering

androidauthority.com·

Pruned YOLOv8 ONNX INT8 Fails: 3 Fixes That Work

💬Prompt Engineering Blog Discussion

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

⚙️AutoML Academic

GGUF vs GPTQ vs AWQ: The Plain-English Guide to LLM Quantization (and Which One to Pick)

💬Prompt Engineering

vettedconsumer.com··Hacker News

NVIDIA五模态压进一套权重

₿Cryptocurrency

ai-brief.liziran.com·

Less-relevant results

The key steps that will enable organizations to scale Physical AI

🧬AGI Self-Evolution

·

Optimal Post-Training Quantization Scales and Where to Find Them

💬Prompt Engineering Academic

两部门：到 2026 年底，人形机器人等重点产品在一批代表性场景中率先完成应用验证和常态部署 - IT之家

₿Cryptocurrency

OpenAI govt stake 🇺🇸, Google compute deal 🚀, Microsoft Scout launch 🤖

🧬AGI Self-Evolution

UniSVQ: 2-bit Unified Scalar-Vector Quantization

🔍Vector Databases Academic

Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive Modeling

💬Prompt Engineering Academic

apple/coreai-models: Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

🧠Symbolic AI Code

github.com··Hacker News

Joint Structural Pruning and Mixed-Precision Quantization for LLM Compression

⚙️AutoML Academic

Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning

⚙️AutoML Academic

Trainable Smooth-Rotation Transforms with Learned Channel Scales for LLM Quantization

⚙️AutoML Academic

LLM Research Papers: The 2026 List (January to May)

🧬AGI Self-Evolution News

magazine.sebastianraschka.com

··Hacker News

Log in to enable infinite scrolling