Linoy Tsaban PRO

linoyts's activity

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

liked a Space about 5 hours ago

Running on Zero

112

👀

Gaze Demo

Gaze detection using Moondream

updated a Space about 8 hours ago

Running on Zero

1

🖌️🏢

Sketch2TRELLIS

3D generation from sketchs with TRELLIS & sdxl

updated a Space about 11 hours ago

Running on A10G

113

🖼️

Edit Friendly Ddpm Inversion

updated a collection 2 days ago

FLUX.1 Tools

Collection

a suite of models designed to add control to the base T2I model FLUX.1, enabling the modification and re-creation of real and generated images • 12 items • Updated 2 days ago

liked 2 models 2 days ago

strangerzonehf/Flux-Sketch-Flat-LoRA

Text-to-Image • Updated 30 days ago • 1.54k • • 29

vikhyatk/moondream2

Image-Text-to-Text • Updated 3 days ago • 108k • 890

liked a Space 4 days ago

Running on L4

160

⚡

Stable Point-Aware 3D

liked a model 4 days ago

stabilityai/stable-point-aware-3d

Image-to-3D • Updated 4 days ago • 1.4k • 105

updated 2 Spaces 4 days ago

Running on Zero

169

⚡️🖋️🌄

Flash Scribble SDXL

Running on Zero

1

🖌️🏢

Sketch2TRELLIS

3D generation from sketchs with TRELLIS & sdxl

upvoted a paper 5 days ago

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Paper • 2501.02976 • Published 6 days ago • 46

liked 4 models 5 days ago

nvidia/Cosmos-1.0-Autoregressive-13B-Video2World

Updated 3 days ago • 280 • 24

nvidia/Cosmos-1.0-Autoregressive-12B

Updated 3 days ago • 266 • 22

nvidia/Cosmos-1.0-Autoregressive-4B

Updated 3 days ago • 625 • 36

nvidia/Cosmos-1.0-Autoregressive-5B-Video2World

Updated 3 days ago • 437 • 20

upvoted a collection 5 days ago

Cosmos

Collection

The collection of Cosmos models • 31 items • Updated 1 day ago • 209

liked a Space 6 days ago

Running

114

👀

Manimator

Transform research papers and mathematical concepts into stu

reacted to lewtun's post with 🔥 6 days ago

view post

Post

3178

I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!

https://x.com/casper_hansen_/status/1875872309996855343

Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!

[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime

See translation

• 

🔥

8

8

🧠

2

2

+

Reply

upvoted a collection 6 days ago

SigLIP

Collection

Contrastive (sigmoid) image-text models from https://arxiv.org/abs/2303.15343 • 10 items • Updated about 1 month ago • 50

liked a Space 6 days ago

Running on L40S

134

🧬🧪🧬

Protein Genesis v2

AI service generating protein structures from user text