📑

AI Paper Research

AI 논문 조사 및 정리

Foundations
멀티모달Multimodal AI
Gemini: A Family of Highly Capable Multi...InternVL: Scaling up Vision Foundation M...
Visual Instruction TuningBLIP-2: Bootstrapping Language-Image Pre...CogVLM: Visual Expert for Pretrained Lan...
Flamingo: a Visual Language Model for Fe...
Learning Transferable Visual Models From...Zero-Shot Text-to-Image GenerationScaling Up Visual and Vision-Language Re...
ViLBERT: Pretraining Task-Agnostic Visio...
홈/멀티모달/2021

멀티모달 — 2021

3편의 논문

ICML 202120,000+

Learning Transferable Visual Models From Natural Language Supervision

자연어 감독으로 전이 가능한 시각 모델 학습

Alec Radford, Jong Wook Kim, Chris Hallacy et al. (2021)

ICML 20215,000+

Zero-Shot Text-to-Image Generation

제로샷 텍스트-이미지 생성

Aditya Ramesh, Mikhail Pavlov, Gabriel Goh et al. (2021)

ICML 20213,000+

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

노이즈가 포함된 텍스트 감독을 활용한 시각 및 비전-언어 표현 학습의 스케일링

Chao Jia, Yinfei Yang, Ye Xia et al. (2021)

← 멀티모달 전체