Encoders - a CCMat Collection

CCMat 's Collections

RL

LoRA

Visual Consistency

ID Preservation

Inference Improvements

Adapters & Controls

Personalization

Depth & Segmentation

Computer Vision

3D & 360 & World Models

Video

Mixture of Experts

Transformers & Attention

StateSpaceModels

LLMs

Audio

Agents

Data

UI

toread

VLM

Encoders

updated Sep 11, 2024

EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters

Paper • 2402.04252 • Published Feb 6, 2024 • 29
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies

Paper • 2404.08197 • Published Apr 12, 2024 • 30