Vasco Ramos

asiimo's activity

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

submitted a paper to Daily Papers about 1 month ago

DEPICT: Scoring Text-to-Image Alignment by Answer Agreement

Paper • 2610.03617 • Published Oct 2 • 2

liked a Space about 1 month ago

Running

289

The ultimate guide to multi-harness RL

🔀

289

Train open models with RL inside real agent harnesses

liked a model 4 months ago

bottlecapai/ThinkingCap-Qwen3.6-27B

Image-Text-to-Text • 27B • Updated Oct 7 • 213 • • 708

updated a dataset 4 months ago

asiimo/genai-bench-sdxl-latents

Viewer • Updated Jul 7 • 16k • 474 • 1

updated a model 4 months ago

asiimo/noisyclip

Zero-Shot Image Classification • 0.4B • Updated Jul 7 • 29

authored 3 papers 4 months ago

Latent Beam Diffusion Models for Generating Visual Sequences

Paper • 2503.20429 • Published Sep 20, 2025

Early Estimation of Language to Latent Alignment in Diffusion Models

Paper • 2512.08505 • Published Jun 28

AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese

Paper • 2603.26511 • Published Mar 27

published a dataset 4 months ago

asiimo/genai-bench-sdxl-latents

Viewer • Updated Jul 7 • 16k • 474 • 1

published a model 5 months ago

asiimo/noisyclip

Zero-Shot Image Classification • 0.4B • Updated Jul 7 • 29

upvoted an article 12 months ago

view article

Article

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

• 

Photoroom

•

Nov 12, 2025

• 102

upvoted an article over 1 year ago

view article

Article

Explaining the SDXL latent space

• 

TimothyAlexisVass

•

May 20, 2024

• 56

authored a paper over 1 year ago

Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis

Paper • 2407.11814 • Published Dec 6, 2024

authored 2 papers over 2 years ago

Generating Coherent Sequences of Visual Illustrations for Real-World Manual Tasks

Paper • 2405.10122 • Published May 16, 2024 • 1

TWIZ-v2: The Wizard of Multimodal Conversational-Stimulus

Paper • 2310.02118 • Published Oct 3, 2023