Oscar Mañas

oscmansan's activity

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

upvoted a paper about 22 hours ago

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

Paper • 2602.00462 • Published 12 days ago • 15

liked a model 6 months ago

openai/gpt-oss-120b

Text Generation • 120B • Updated Aug 26, 2025 • 3.33M • • 4.47k

upvoted a paper 6 months ago

Controlling Multimodal LLMs via Reward-guided Decoding

Paper • 2508.11616 • Published Aug 15, 2025 • 7

authored a paper 6 months ago

Controlling Multimodal LLMs via Reward-guided Decoding

Paper • 2508.11616 • Published Aug 15, 2025 • 7

commented a paper 6 months ago

Controlling Multimodal LLMs via Reward-guided Decoding

Paper • 2508.11616 • Published Aug 15, 2025 • 7 •

2

liked 3 datasets 10 months ago

facebook/PLM-Image-Auto

Viewer • Updated Apr 21, 2025 • 30.3M • 427 • 16

google/docci

Updated Jul 24, 2024 • 343 • 75

google/imageinwords

Updated May 25, 2024 • 92 • 120

liked a Space 12 months ago

Running

648

AI Deadlines

⚡

648

View upcoming AI conference deadlines in one place

authored a paper about 1 year ago

Consistency-diversity-realism Pareto fronts of conditional image generative models

Paper • 2406.10429 • Published Jun 14, 2024

liked a Space about 1 year ago

Running

592

Scaling test-time compute

📈

592

Run advanced LLM search strategies to boost problem solving

liked a model about 1 year ago

google/paligemma2-3b-pt-224

Image-Text-to-Text • 3B • Updated Dec 5, 2024 • 30.3k • 162

liked 5 models over 1 year ago

allenai/Molmo-72B-0924

Image-Text-to-Text • 73B • Updated Oct 9, 2025 • 5.85k • 296

meta-llama/Llama-3.2-90B-Vision-Instruct

Image-Text-to-Text • 89B • Updated Mar 4, 2025 • 2.52k • • 349

mistralai/Pixtral-12B-2409

Updated Jul 28, 2025 • 17.7k • 674

facebook/chameleon-30b

Image-Text-to-Text • 34B • Updated Jul 30, 2024 • 25 • 88

HuggingFaceM4/Idefics3-8B-Llama3

Image-Text-to-Text • 8B • Updated Dec 2, 2024 • 151k • 302

upvoted an article over 1 year ago

view article

Article

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

• 
• 

Jul 25, 2024

•

17

liked 2 models over 1 year ago

meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.47M • • 5.44k

google/gemma-2-9b

Text Generation • 9B • Updated Aug 7, 2024 • 53.6k • • 689