S.F.

search-facility's activity

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

upvoted 3 papers 5 days ago

Fish Audio S2 Technical Report

Paper • 2603.08823 • Published 7 days ago • 27

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

Paper • 2603.09095 • Published 7 days ago • 26

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

Paper • 2603.06577 • Published 10 days ago • 43

upvoted 2 papers 6 days ago

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

Paper • 2603.07660 • Published 8 days ago • 79

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

Paper • 2603.05890 • Published 11 days ago • 83

upvoted 2 papers 7 days ago

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published 17 days ago • 35

Reasoning Models Struggle to Control their Chains of Thought

Paper • 2603.05706 • Published 11 days ago • 28

upvoted a collection 12 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 1 day ago • 22

upvoted a paper 14 days ago

Mode Seeking meets Mean Seeking for Fast Long Video Generation

Paper • 2602.24289 • Published 17 days ago • 39

upvoted a paper 17 days ago

Image Generation with a Sphere Encoder

Paper • 2602.15030 • Published 28 days ago • 15

upvoted 4 papers 18 days ago

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

Paper • 2602.19163 • Published 23 days ago • 14

Solaris: Building a Multiplayer Video World Model in Minecraft

Paper • 2602.22208 • Published 19 days ago • 28

DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation

Paper • 2602.12160 • Published Feb 12 • 38

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Paper • 2602.22190 • Published 19 days ago • 15

upvoted 4 papers 26 days ago

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression

Paper • 2602.15200 • Published 28 days ago • 7

Revisiting the Platonic Representation Hypothesis: An Aristotelian View

Paper • 2602.14486 • Published 29 days ago • 11

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published 27 days ago • 110

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Paper • 2602.14111 • Published 30 days ago • 55

liked a model 28 days ago

shallowdream204/BitDance-14B-16x

Text-to-Image • 15B • Updated 27 days ago • 277 • 89

upvoted a paper 28 days ago

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

Paper • 2602.11858 • Published Feb 12 • 59