johko (Johannes Kolbe)

upvoted an article 19 days ago

Article

Design choices for Vision Language Models in 2024

By

•

20 days ago

• 17

upvoted a collection about 1 month ago

🎭 Avatars

Collection

The latest AI-powered technologies usher in a new era of realistic avatars! 🚀 • 31 items • Updated about 14 hours ago • 30

upvoted a paper about 1 month ago

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

Paper • 2403.10516 • Published Mar 15 • 15

upvoted a collection about 2 months ago

Matryoshka Embedding Models

Collection

https://huggingface.co/blog/matryoshka • 11 items • Updated Mar 27 • 10

upvoted 2 papers 2 months ago

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts

Paper • 2402.13220 • Published Feb 20 • 12

Aria Everyday Activities Dataset

Paper • 2402.13349 • Published Feb 20 • 28

upvoted a paper 3 months ago

PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models

Paper • 2402.01118 • Published Feb 2 • 28

upvoted a collection 3 months ago

AIM

Collection

AIM: Autoregressive Image Models • 5 items • Updated Jan 29 • 43

upvoted a paper 4 months ago

Instruct-Imagen: Image Generation with Multi-modal Instruction

Paper • 2401.01952 • Published Jan 3 • 29

upvoted 5 papers 5 months ago

upvoted 3 papers 6 months ago

GLaMM: Pixel Grounding Large Multimodal Model

Paper • 2311.03356 • Published Nov 6, 2023 • 31

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?

Paper • 2311.00047 • Published Oct 31, 2023 • 7

Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

Paper • 2311.00430 • Published Nov 1, 2023 • 53

upvoted a paper 7 months ago

VidChapters-7M: Video Chapters at Scale

Paper • 2309.13952 • Published Sep 25, 2023 • 8

upvoted 2 papers 8 months ago

Kosmos-2.5: A Multimodal Literate Model

Paper • 2309.11419 • Published Sep 20, 2023 • 47

An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models

Paper • 2309.09958 • Published Sep 18, 2023 • 18

upvoted a paper 11 months ago

Recognize Anything: A Strong Image Tagging Model

Paper • 2306.03514 • Published Jun 6, 2023 • 9

Johannes Kolbe

AI & ML interests

Organizations

johko's activity

Design choices for Vision Language Models in 2024

🎭 Avatars

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

Matryoshka Embedding Models

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts

Aria Everyday Activities Dataset

PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models

AIM

Instruct-Imagen: Image Generation with Multi-modal Instruction

PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

Describing Differences in Image Sets with Natural Language

FaceStudio: Put Your Face Everywhere in Seconds

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

GAIA: a benchmark for General AI Assistants

GLaMM: Pixel Grounding Large Multimodal Model

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?

Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling

VidChapters-7M: Video Chapters at Scale

Kosmos-2.5: A Multimodal Literate Model

An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models

Recognize Anything: A Strong Image Tagging Model