NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks Paper • 2410.20650 • Published 11 days ago • 13
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 3 days ago • 157
LayerSkip Collection Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated 12 days ago • 42
DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes Paper • 2410.18084 • Published 15 days ago • 12
Remember, Retrieve and Generate: Understanding Infinite Visual Concepts as Your Personalized Assistant Paper • 2410.13360 • Published 21 days ago • 8
MobA: A Two-Level Agent System for Efficient Mobile Task Automation Paper • 2410.13757 • Published 21 days ago • 30
Addition is All You Need for Energy-efficient Language Models Paper • 2410.00907 • Published Oct 1 • 143
SyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs Paper • 2410.00337 • Published Oct 1 • 10
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion Paper • 2409.11406 • Published Sep 17 • 25