⚗️ Knowledge Distillation - hop1.ng.1357 · Scour

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

🤖AI News Blog

blog.google··Hacker News

Less-relevant results

Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters

🧠Machine Learning Academic

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

⚡Edge AI Code

github.com··Hacker News

Knowledge Distillation for Visual Autoregressive Models

🖼️Multimodal AI Academic

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

🤖LLM Academic

SecRL-Prune: Structured Reinforcement Learning-Based Pruning of CodeLLMs for Preserving Adversarial Code Mutation

🔐Cryptography Academic

TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies

🖼️Multimodal AI Academic

No more posts from hop1.ng.1357's subscribed feeds.

Scour all 25255 feeds Learn more about Feeds

Log in to enable infinite scrolling