S.F.

search-facility's activity

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

upvoted a paper about 4 hours ago

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

Paper • 2603.19598 • Published 5 days ago • 30

upvoted 2 papers 4 days ago

LoST: Level of Semantics Tokenization for 3D Shapes

Paper • 2603.17995 • Published 6 days ago • 30

Complementary Reinforcement Learning

Paper • 2603.17621 • Published 6 days ago • 34

upvoted a paper 5 days ago

InCoder-32B: Code Foundation Model for Industrial Scenarios

Paper • 2603.16790 • Published 7 days ago • 296

upvoted 3 papers 6 days ago

Mixture-of-Depths Attention

Paper • 2603.15619 • Published 8 days ago • 77

Attention Residuals

Paper • 2603.15031 • Published 8 days ago • 154

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published 8 days ago • 145

upvoted a paper 7 days ago

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation

Paper • 2603.11647 • Published 12 days ago • 31

upvoted 3 papers 12 days ago

Fish Audio S2 Technical Report

Paper • 2603.08823 • Published 15 days ago • 35

Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs

Paper • 2603.09095 • Published 15 days ago • 28

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Paper • 2603.06577 • Published 18 days ago • 48

upvoted 2 papers 13 days ago

Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

Paper • 2603.07660 • Published 16 days ago • 83

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 19 days ago • 91

upvoted 2 papers 14 days ago

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published 24 days ago • 37

Reasoning Models Struggle to Control their Chains of Thought

Paper • 2603.05706 • Published 19 days ago • 34

upvoted a collection 20 days ago

Helios

Collection

Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated 9 days ago • 24

upvoted a paper 21 days ago

Mode Seeking meets Mean Seeking for Fast Long Video Generation

Paper • 2602.24289 • Published 25 days ago • 41

upvoted 3 papers 25 days ago

Image Generation with a Sphere Encoder

Paper • 2602.15030 • Published Feb 16 • 15

JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation

Paper • 2602.19163 • Published about 1 month ago • 14

Solaris: Building a Multiplayer Video World Model in Minecraft

Paper • 2602.22208 • Published 27 days ago • 28