S.F.

search-facility's activity

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

upvoted a paper 4 days ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 7 days ago • 577

upvoted 2 papers 5 days ago

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Paper • 2609.34981 • Published 7 days ago • 136

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 8 days ago • 138

upvoted 2 papers 6 days ago

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

Paper • 2609.35767 • Published 8 days ago • 49

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

Paper • 2609.33757 • Published 9 days ago • 245

upvoted 2 papers 7 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 11 days ago • 160

Disaggregated Quantization: Specializing LLM Prefill and Decode

Paper • 2609.26333 • Published 14 days ago • 92

upvoted a paper 10 days ago

Coding Agents for Generalized Task and Motion Planning Problems

Paper • 2609.30233 • Published 12 days ago • 28

upvoted 6 papers 12 days ago

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

Paper • 2609.26774 • Published 14 days ago • 56

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published 15 days ago • 77

Bellman Policy Optimization

Paper • 2609.15987 • Published 22 days ago • 49

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

Paper • 2609.24058 • Published 15 days ago • 55

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Paper • 2609.24981 • Published 15 days ago • 74

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 14 days ago • 163

upvoted a paper 13 days ago

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 15 days ago • 222

upvoted 2 papers 17 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 19 days ago • 224

Self-Evolving Search Index

Paper • 2609.19656 • Published 19 days ago • 63

upvoted 3 papers 18 days ago

StepAudio 3 Music Technical Report

Paper • 2609.16034 • Published 25 days ago • 110

RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs

Paper • 2609.12552 • Published 25 days ago • 8

Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

Paper • 2609.17909 • Published 21 days ago • 47