Alara Dirik

adirik's activity

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

upvoted a paper 5 days ago

Repurposing Geometric Foundation Models for Multi-view Diffusion

Paper • 2603.22275 • Published 7 days ago • 45

upvoted a paper 11 days ago

Utonia: Toward One Encoder for All Point Clouds

Paper • 2603.03283 • Published 27 days ago • 184

upvoted a paper 14 days ago

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time

Paper • 2512.08924 • Published Dec 9, 2025 • 21

upvoted 2 papers 17 days ago

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

Paper • 2603.03143 • Published 27 days ago • 145

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published 21 days ago • 81

upvoted a paper 23 days ago

dLLM: Simple Diffusion Language Modeling

Paper • 2602.22661 • Published Feb 26 • 152

upvoted 2 papers about 1 month ago

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Paper • 2312.02145 • Published Dec 4, 2023 • 8

Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Paper • 2602.12280 • Published Feb 12 • 34

upvoted an article 3 months ago

view article

Article

Introduction to 3D Gaussian Splatting

• 

Sep 18, 2023

•

131

upvoted an article 4 months ago

view article

Article

We’re open-sourcing our text-to-image model and the process behind it

• 

Nov 12, 2025

•

96

upvoted a collection 4 months ago

CoVT: Chain-of-Visual-Thought

Collection

Enrich VLMs’ vision-centric reasoning capabilities via Chain-of-Visual-Thought! • 7 items • Updated Nov 25, 2025 • 6

upvoted a paper 4 months ago

Φeat: Physically-Grounded Feature Representation

Paper • 2511.11270 • Published Nov 14, 2025 • 11

upvoted 5 articles 8 months ago

view article

Article

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

• 

Feb 7, 2025

•

282

view article

Article

FineVideo: behind the scenes

• 
• 
• +4

Sep 23, 2024

•

35

view article

Article

CinePile 2.0 - making stronger datasets with adversarial refinement

• 
• 
• +2

Oct 23, 2024

•

19

view article

Article

TimeScope: How Long Can Your Video Large Multimodal Model Go?

• 
• 
• +2

Jul 23, 2025

•

48

view article

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

• 
• 
• +1

May 14, 2024

•

285

upvoted 3 collections 10 months ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 200

Any-to-Any Models, Datasets, Spaces

Collection

19 items • Updated Feb 9 • 30

Qwen3-Embedding

Collection

6 items • Updated Dec 31, 2025 • 154