2 26 31

Michael Toker

tokeron

https://tokeron.github.io/

AI & ML interests

NLP, Computer Vision, Text to Image, LLMs, VLMs, Interpretability, Explainability

Recent Activity

upvoted a paper 9 days ago

Emu3.5: Native Multimodal Models are World Learners

liked a model about 2 months ago

Lightricks/LTX-2

upvoted a collection about 2 months ago

SANA-Video

View all activity

Organizations

liked a model about 2 months ago

Lightricks/LTX-2

Image-to-Video • Updated 4 days ago • 1.93M • • 1.59k

liked a model 9 months ago

fal/AuraFlow

Text-to-Image • Updated Jul 18, 2024 • 310 • • 655

liked a Space 10 months ago

Inner Lexicon

😻

demonstrating how the model retrieve words by sub-word token

liked a model about 1 year ago

OpenGVLab/InternVL2_5-8B-MPO

Image-Text-to-Text • 8B • Updated Mar 25, 2025 • 808 • 48

liked a model over 1 year ago

Lightricks/LTX-Video

Image-to-Video • Updated Jul 16, 2025 • 346k • • 2.11k

liked a dataset over 1 year ago

MorVentura/NL-Eye

Viewer • Updated Oct 16, 2024 • 350 • 46 • 3

liked a model over 1 year ago

deepseek-ai/Janus-1.3B

Any-to-Any • Updated Jan 27, 2025 • 5.06k • 593

liked a Space over 1 year ago

Latent Navigation

🪐

281

Travel through the model latent space

liked 7 models over 1 year ago

liked a dataset almost 2 years ago

nyu-mll/multi_nli

Viewer • Updated Jan 4, 2024 • 412k • 3.05k • 108

liked a model almost 2 years ago

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • 8B • Updated Jun 18, 2025 • 1.33M • • 4.39k

liked 2 Spaces almost 2 years ago

Real-Time Text-to-Image SDXL Lightning

⚡

617

Real-Time Image Generation with SDXL Lightning

DiffusionLens

🔍

Generate images from text prompts using intermediate layers of text encoders