Yeha Kim PRO

yeha's activity

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

upvoted an article about 19 hours ago

view article

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

• 
• 
• +5

6 days ago

•

743

upvoted a collection about 19 hours ago

Cosmos-Predict2.5

Collection

Improved World Simulation with Video Foundation Models for Physical AI • 2 items • Updated 1 day ago • 19

liked a model about 23 hours ago

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 6 days ago • 884k • • 1.35k

upvoted a paper 1 day ago

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Paper • 2509.19296 • Published Sep 23, 2025 • 27

liked a model 20 days ago

robbyant/lingbot-world-base-act

Image-to-Video • Updated Mar 5 • 16

liked a dataset 22 days ago

ropedia-ai/xperience-10m

Updated 19 days ago • 2.24M • 156

upvoted a paper about 1 month ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published Mar 4 • 185

liked a model about 1 month ago

zhuhz22/Causal-Forcing

Text-to-Video • Updated Feb 7 • 7

liked 3 models about 2 months ago

nvidia/DreamDojo

Updated Feb 23 • 44 • 30

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated 24 days ago • 997k • • 1.42k

robbyant/lingbot-world-base-cam

Image-to-Video • Updated Feb 2 • 330

upvoted a collection about 2 months ago

LingBot-World

Collection

3 items • Updated 6 days ago • 37

liked a dataset 2 months ago

phyworldbench/phyworldbench

Viewer • Updated May 16, 2025 • 350 • 24 • 4

liked a Space 2 months ago

Running on Zero

Featured

1.83k

Qwen3-TTS Demo

🎙

1.83k

Generate speech from text with custom voice, cloning, or presets

liked a model 4 months ago

Qwen/Qwen2.5-VL-32B-Instruct

Image-Text-to-Text • 33B • Updated Apr 14, 2025 • 63.3k • 478

upvoted a paper 4 months ago

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published Nov 25, 2025 • 50

liked a Space 4 months ago

Running on Zero

Featured

808

FLUX.2 [dev]

💻

808

Generate or edit images from text prompts with optional pictures

liked 2 models 4 months ago

MachineDelusions/Qwen-Edit-Loras

Updated Nov 22, 2025 • 36

facebook/sam3

Mask Generation • 0.9B • Updated Nov 20, 2025 • 2.5M • 1.84k

upvoted a collection 5 months ago

PS3: Scaling Vision Pre-Training to 4K Resolution

Collection

Enabling 4k resolution for VLMs, CVPR 2025, https://nvlabs.github.io/PS3/ • 15 items • Updated 1 day ago • 9