S.F.

search-facility's activity

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

upvoted 2 papers about 24 hours ago

Generative Modeling with Orbit-Space Particle Flow Matching

Paper • 2605.02222 • Published 3 days ago • 4

MolmoAct2: Action Reasoning Models for Real-world Deployment

Paper • 2605.02881 • Published 3 days ago • 204

upvoted 3 papers 2 days ago

When Do Diffusion Models learn to Generate Multiple Objects?

Paper • 2605.00273 • Published 7 days ago • 7

Map2World: Segment Map Conditioned Text to 3D World Generation

Paper • 2605.00781 • Published 6 days ago • 24

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

Paper • 2605.00658 • Published 6 days ago • 79

upvoted 2 papers 8 days ago

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

Paper • 2604.24763 • Published 10 days ago • 68

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

Paper • 2604.24764 • Published 10 days ago • 116

upvoted 2 papers 9 days ago

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

Paper • 2604.22294 • Published 13 days ago • 16

FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing

Paper • 2604.22586 • Published 13 days ago • 16

upvoted 3 papers 16 days ago

Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems

Paper • 2604.04936 • Published Jan 8 • 26

(1D) Ordered Tokens Enable Efficient Test-Time Search

Paper • 2604.15453 • Published 21 days ago • 18

Qwen3.5-Omni Technical Report

Paper • 2604.15804 • Published 20 days ago • 58

upvoted a paper 21 days ago

Lyra 2.0: Explorable Generative 3D Worlds

Paper • 2604.13036 • Published 23 days ago • 41

upvoted 4 papers 22 days ago

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

Paper • 2604.08121 • Published 28 days ago • 43

CodeTracer: Towards Traceable Agent States

Paper • 2604.11641 • Published 24 days ago • 38

Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music

Paper • 2604.10905 • Published 24 days ago • 28

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published 24 days ago • 141

upvoted 2 papers 27 days ago

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published about 1 month ago • 66

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Paper • 2604.04746 • Published 29 days ago • 71

upvoted a paper 29 days ago

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published Apr 4 • 38