Florian

hlzl's activity

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

upvoted a paper 8 days ago

SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

Paper • 2306.14610 • Published Jun 26, 2023 • 2

liked a model 12 days ago

facebook/dinov3-convnext-small-pretrain-lvd1689m

Image Feature Extraction • 49.5M • Updated Aug 19, 2025 • 15.9k • 25

upvoted a collection 15 days ago

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated Mar 2 • 88

liked a dataset about 2 months ago

allenai/pixmo-cap

Viewer • Updated Nov 27, 2024 • 717k • 1.69k • 39

upvoted a paper 2 months ago

LlamaFusion: Adapting Pretrained Language Models for Multimodal Generation

Paper • 2412.15188 • Published Dec 19, 2024 • 2

upvoted an article 2 months ago

view article

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

• 
• 
• +5

May 21, 2025

•

254

authored a paper 5 months ago

Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks

Paper • 2510.25480 • Published Oct 29, 2025

liked a Space 5 months ago

Running

221

FineVision: Open Data is All You Need

📝

221

A new open-source dataset for training VLMs

authored a paper 7 months ago

Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models

Paper • 2301.13104 • Published Jan 30, 2023

upvoted a paper 7 months ago

MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis

Paper • 2509.06617 • Published Sep 8, 2025 • 1

liked a dataset 7 months ago

HuggingFaceM4/FineVision

Viewer • Updated Oct 21, 2025 • 24.2M • 140k • 479

liked a Space 7 months ago

Running on CPU Upgrade

1k

Open VLM Leaderboard

🌎

1k

VLMEvalKit Evaluation Results Collection