Marcus Gawronsky

marcusinthesky's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 7 days ago

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers

Paper • 2504.10483 • Published 10 days ago • 20

liked 2 models 11 days ago

lucasjin/Namo-500M-V1

Updated Feb 21 • 99 • 11

OpenGVLab/InternVL3-1B

Image-Text-to-Text • Updated 7 days ago • 13.7k • 48

upvoted a paper 18 days ago

Multi-Token Attention

Paper • 2504.00927 • Published 23 days ago • 46

liked a model 18 days ago

meta-llama/Llama-4-Scout-17B-16E-Instruct

Image-Text-to-Text • Updated 15 days ago • 782k • • 824

liked a model 23 days ago

vidore/ColSmolVLM-Instruct-256M-base

Updated 10 days ago • 2

liked a model 26 days ago

ZinengTang/tulip-tokenizer

Updated Mar 20 • 1

upvoted 2 papers about 1 month ago

TULIP: Towards Unified Language-Image Pretraining

Paper • 2503.15485 • Published Mar 19 • 48

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13 • 160

liked 6 models about 1 month ago

zhibinlan/LLaVE-0.5B

Image-Text-to-Text • Updated Mar 14 • 3.15k • 7

HuggingFaceTB/SmolVLM2-256M-Video-Instruct

Image-Text-to-Text • Updated 16 days ago • 19.3k • 53

allenai/OLMo-2-0325-32B-Instruct

Text Generation • Updated Mar 14 • 5.25k • 127

Stanford-ILIAD/prism-qwen25-extra-dinosiglip-224px-0_5b

Image-Text-to-Text • Updated Dec 12, 2024 • 741 • 2

google/siglip2-base-patch16-naflex

Zero-Shot Image Classification • Updated Feb 21 • 17.7k • 5

google/gemma-3-1b-it

Text Generation • Updated 20 days ago • 2.01M • 335

liked 2 models about 2 months ago

facebook/drama-large

Sentence Similarity • Updated Mar 4 • 69 • 7

chandar-lab/NeoBERT

Feature Extraction • Updated about 1 month ago • 3.12k • 103

liked 2 models 2 months ago

nvidia/MambaVision-B-1K

Image Classification • Updated 28 days ago • 1.08k • 11

OpenGVLab/HoVLE

Image-Text-to-Text • Updated Dec 24, 2024 • 252 • 10

upvoted a paper 2 months ago

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Paper • 2502.08468 • Published Feb 12 • 13