Deniz Aybey PRO

denizaybey's activity

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

upvoted a collection 1 day ago

ThinkLite-VL

Collection

4 items • Updated 1 day ago • 2

liked a model 1 day ago

russwang/ThinkLite-VL-7B

Updated about 15 hours ago • 13 • 4

upvoted a collection 1 day ago

Orpheus Multilingual Research Release

Collection

Beta Release of multilingual models. • 12 items • Updated 2 days ago • 66

liked 2 models 2 days ago

nvidia/C-RADIOv2-g

Updated 2 days ago • 250 • 10

moonshotai/Kimi-VL-A3B-Thinking

Image-Text-to-Text • Updated about 9 hours ago • 3.19k • 212

upvoted 2 papers 3 days ago

Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

Paper • 2504.05599 • Published 5 days ago • 73

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published 4 days ago • 127

liked a Space 6 days ago

Running on CPU Upgrade

120

120

Try YourBench!

🪄

Generate a custom benchmark from any document

liked 4 models 6 days ago

reducto/RolmOCR

Image-Text-to-Text • Updated 10 days ago • 5.44k • 331

ByteDance/MegaTTS3

Text-to-Speech • Updated 8 days ago • 2.52k • 326

meta-llama/Llama-4-Maverick-17B-128E-Instruct

Image-Text-to-Text • Updated 3 days ago • 26.8k • • 284

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

Image-Text-to-Text • Updated 3 days ago • 445k • • 743

liked a model 10 days ago

DataoceanAI/dolphin-small

Automatic Speech Recognition • Updated 17 days ago • 167 • 23

liked a model 11 days ago

all-hands/openhands-lm-32b-v0.1

Text Generation • Updated 9 days ago • 53.4k • 330

liked a model 16 days ago

manycore-research/SpatialLM-Llama-1B

Text Generation • Updated 23 days ago • 18k • 933

liked a model 17 days ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated 1 day ago • 125k • 1.34k

liked a model 18 days ago

starvector/starvector-8b-im2svg

Text Generation • Updated 24 days ago • 42.8k • 437

liked a Space 18 days ago

Running

253

253

starvector-1b-im2svg

📈

Convert images and text into scalable vector graphics (SVG) code

upvoted 2 collections 18 days ago

MoshiVis v0.1

Collection

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 8 items • Updated 22 days ago • 22

MambaVision

Collection

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. • 13 items • Updated 2 days ago • 31