merve/my-first-bucket
0 Bytes
merve PRO
merve
AI & ML interests
I love this website
VLMs, vision & co
Recent Activity
new activity 3 minutes ago
lerobot/pi0fast-base:Add eval results for VLABench new activity 3 minutes ago
nvidia/GR00T-N1-2B:Add eval results for VLABench new activity 3 minutes ago
lerobot/pi05_base:Add eval results for VLABenchOrganizations
![Unofficial Mistral Community [deprecated]'s profile picture](https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/HAdAzcs1CDB9OxgxT2W9K.png)
Posts 162
Post
11513
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
Articles 45
Article
867
Welcome Gemma 4: Frontier multimodal intelligence on device
Curated collection of notable models and spaces from the week of April 17.
-
OpenMOSS-Team/MOSS-Audio-4B-Instruct
Audio-Text-to-Text • 5B • Updated • 382 • 28 -
OpenMOSS-Team/MOSS-Audio-8B-Thinking
Audio-Text-to-Text • 9B • Updated • 493 • 39 -
bytedance-research/Timer-S1
Time Series Forecasting • 8B • Updated • 1.51k • 19 -
BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
25B • Updated • 17.1k • 51
Curated collection of notable models and spaces from the week of April 17.
Curated collection of notable models and spaces from the week of April 17.
-
OpenMOSS-Team/MOSS-Audio-4B-Instruct
Audio-Text-to-Text • 5B • Updated • 382 • 28 -
OpenMOSS-Team/MOSS-Audio-8B-Thinking
Audio-Text-to-Text • 9B • Updated • 493 • 39 -
bytedance-research/Timer-S1
Time Series Forecasting • 8B • Updated • 1.51k • 19 -
BugTraceAI/BugTraceAI-Apex-G4-26B-Q4
25B • Updated • 17.1k • 51
spaces 120
pinned
Running
Agents
1
Background Removal
🌘
pinned
Running
114
Vision Papers
💻
All paper summaries read by Merve
Running
Agents
Trackio 2
🚀
Running on CPU Upgrade
Agents
18
Daggr Image To 3d
👀
Convert images into 3D assets with background removal and enhancement
Running on Zero
Agents
2
FASHN VTON v1.5
👗
Maskless try-on directly in pixel space
Sleeping
Agents
Daggr Image To 3d
👀
models 138
merve/fistik
Updated
merve/gemma4-multiimage-thinking-lora
Updated • 1
merve/rtdetr_v2_r50vd-mobile-ui-design
Object Detection • 42.9M • Updated • 426 • 1
merve/kosmos2_5
Updated
merve/rtdetr-v2-mobile-ui-final
Updated
merve/sam2-large-micromat
Image Segmentation • 0.2B • Updated • 35 • 1
merve/mobile-ui-rtdetrv2
Object Detection • 20.1M • Updated • 5
merve/openscene-vit-dinov3
Image Classification • 85.6M • Updated • 30
merve/license-plates-rtdetrv2
Object Detection • 20.1M • Updated • 6
merve/food101-vit-dinov3
Image Classification • 85.7M • Updated • 195
datasets 49
merve/agent_traces
Traces • Updated • 1 • 69
merve/Molmo2-SynMultiImageQA-tiny
Viewer • Updated • 9.8k • 40
merve/cosyn400k-tiny
Viewer • Updated • 5.84k • 73 • 1
merve/vlm_test_images
Viewer • Updated • 31 • 309k • 6
merve/pixmo-cap-tiny
Viewer • Updated • 7.17k • 31
merve/pixmo-cap-small
Viewer • Updated • 35.9k • 56 • 1
merve/MolmoWeb-SyntheticGround-small
Viewer • Updated • 3.3k • 71
merve/license-plates-coco
Viewer • Updated • 6.18k • 30
merve/license-plates-tfod
Viewer • Updated • 6.18k • 20 • 1
merve/license-plates-voc
Viewer • Updated • 6.18k • 24 • 1