Alara Dirik

adirik's activity

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

liked a Space 1 day ago

Running

71

SmolVLM 256M Instruct WebGPU

🐨

71

Generate captions for your images instantly

liked a model 2 days ago

nvidia/audio-flamingo-next-hf

Audio-Text-to-Text • 8B • Updated 5 days ago • 1.95k • 36

liked a Space 3 days ago

Running

143

Bonsai 1-bit WebGPU

🌳

143

Run 1-bit Bonsai LLMs locally in your browser on WebGPU

liked a model 5 days ago

tencent/HY-World-2.0

Image-to-3D • Updated 5 days ago • 498

updated a model 11 days ago

adirik/InternVL2_5-4B-Intrinsic-Judge

4B • Updated 11 days ago • 115

liked a model 13 days ago

facebook/tribev2

Updated 25 days ago • 144k • 408

liked a Space 15 days ago

Running

30

FlashWorld Demo Spark

📈

30

Spark frontend for FlashWorld

published a model 17 days ago

adirik/InternVL2_5-4B-Intrinsic-Judge

4B • Updated 11 days ago • 115

liked a Space 17 days ago

Running on Zero

Agents

77

VOID

👀

77

VOID: Video Object and Interaction Deletion

liked a model 17 days ago

netflix/void-model

Video-to-Video • Updated 14 days ago • 882

liked a Space 18 days ago

Running on Zero

MCP

9

Map Anything (v1)

🏃

9

Universal Feed-Forward Metric 3D Reconstruction

liked a model 18 days ago

CohereLabs/cohere-transcribe-03-2026

Automatic Speech Recognition • Updated 1 day ago • 269k • 894

liked a model 19 days ago

facebook/sam3.1

Mask Generation • Updated 24 days ago • 43.6k • 200

upvoted a paper 21 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published 25 days ago • 156

upvoted a paper 26 days ago

Repurposing Geometric Foundation Models for Multi-view Diffusion

Paper • 2603.22275 • Published 28 days ago • 47

liked a model 28 days ago

facebook/map-anything

Image-to-3D • 1B • Updated Jan 20 • 73.8k • 89

authored a paper 29 days ago

ReasonX: MLLM-Guided Intrinsic Image Decomposition

Paper • 2512.04222 • Published Dec 3, 2025

liked a model about 1 month ago

facebook/map-anything-v1

Image-to-3D • 0.6B • Updated Dec 19, 2025 • 2.39k • 26

upvoted a paper about 1 month ago

Utonia: Toward One Encoder for All Point Clouds

Paper • 2603.03283 • Published Mar 3 • 185

authored a paper about 1 month ago

PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling

Paper • 2504.14219 • Published Apr 19, 2025 • 2