S.F.

search-facility's activity

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

upvoted 2 papers about 4 hours ago

Toto 2.0: Time Series Forecasting Enters the Scaling Era

Paper • 2605.20119 • Published 4 days ago • 34

Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Paper • 2605.18233 • Published 5 days ago • 87

upvoted 5 papers 1 day ago

Reinforcement Learning via Self-Distillation

Paper • 2601.20802 • Published Jan 28 • 47

GATES: Self-Distillation under Privileged Context with Consensus Gating

Paper • 2602.20574 • Published Feb 24 • 1

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published 11 days ago • 186

When Vision Speaks for Sound

Paper • 2605.16403 • Published 10 days ago • 95

Active Learners as Efficient PRP Rerankers

Paper • 2605.14236 • Published 8 days ago • 93

upvoted a paper 7 days ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 10 days ago • 58

liked a model 8 days ago

circlestone-labs/Anima

Updated 8 days ago • 602k • 1.49k

upvoted 2 papers 9 days ago

Pixal3D: Pixel-Aligned 3D Generation from Images

Paper • 2605.10922 • Published 12 days ago • 31

Qwen-Image-2.0 Technical Report

Paper • 2605.10730 • Published 12 days ago • 106

upvoted a paper 14 days ago

RLDX-1 Technical Report

Paper • 2605.03269 • Published 18 days ago • 122

upvoted 2 papers 16 days ago

Generative Modeling with Orbit-Space Particle Flow Matching

Paper • 2605.02222 • Published 19 days ago • 9

MolmoAct2: Action Reasoning Models for Real-world Deployment

Paper • 2605.02881 • Published 19 days ago • 333

upvoted 3 papers 17 days ago

When Do Diffusion Models learn to Generate Multiple Objects?

Paper • 2605.00273 • Published 23 days ago • 9

Map2World: Segment Map Conditioned Text to 3D World Generation

Paper • 2605.00781 • Published 22 days ago • 25

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

Paper • 2605.00658 • Published 22 days ago • 84

upvoted 2 papers 23 days ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 26 days ago • 71

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published 26 days ago • 118

upvoted a paper 24 days ago

Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets

Paper • 2604.22294 • Published 29 days ago • 17