Daniel van Strien PRO

davanstrien's activity

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

upvoted a collection 19 minutes ago

MobileMoE

Collection

a family of on-device MoE language models with sub-billion active parameters (0.3-0.9B active and 1.3-5.3B total) that establish a new Pareto frontier • 11 items • Updated about 16 hours ago • 11

upvoted 2 collections 5 days ago

Encyclopaedia Britannica illustrations, 1768–1929

Collection

Illustrated pages across every out-of-copyright Britannica edition: the page classifier, the 115k pages it found, and the NLS labels it learned from. • 3 items • Updated 7 days ago • 2

NuExtract3

Collection

12 items • Updated May 26 • 16

upvoted an article 6 days ago

view article

Article

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

• 

tomaarsen

•

6 days ago

• 105

upvoted a collection 7 days ago

GLiNER2.5 Models

Collection

3 items • Updated 8 days ago • 10

upvoted an article 7 days ago

view article

Article

Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC

• 

ibm-granite

•

7 days ago

• 30

upvoted an article 11 days ago

view article

Article

NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics

• 

nvidia

•

Jul 27

• 77

upvoted a collection 11 days ago

EgoSuite-Open100K

Collection

The largest fully-annotated open egocentric human dataset. 100,000 hours across 15,000+ tasks and scenes. • 3 items • Updated 13 days ago • 50

upvoted a collection 13 days ago

Ornith-1.5

Collection

13 items • Updated 6 days ago • 149

upvoted an article 14 days ago

view article

Article

~Don't~ Repeat Yourself

• 

patrickvonplaten

•

Apr 5, 2022

• 56

upvoted a collection 18 days ago

NaFlexCLAP

Collection

Experiments in OpenCLIP (main branch) with `timm` NaFlexViT audio encoder + modern text encoder for variable-time , variable-length text CLAP models • 4 items • Updated 22 days ago • 3

upvoted a paper 19 days ago

ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval

Paper • 2505.17166 • Published May 22, 2025 • 2

upvoted an article 19 days ago

view article

Article

Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

• 

amazon

•

19 days ago

• 32

upvoted a paper 19 days ago

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 42

upvoted 2 articles 20 days ago

view article

Article

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

• 

CohereLabs

•

20 days ago

• 39

view article

Article

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

• 

LiquidAI

•

20 days ago

• 49

upvoted a paper 22 days ago

QueenVIS: Rethinking Image-Only Training for Video Instance Segmentation via Query Enrichment

Paper • 2607.24598 • Published Jul 27 • 9

upvoted 3 collections 22 days ago

Muse Glimmer

Collection

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated 22 days ago • 106

Chronicling America, 1770-1810

Collection

3 items • Updated Apr 9 • 1

Revolutionary War Pension Files

Collection

3 items • Updated Jun 11 • 1