CutClaw: Agentic Hours-Long Video Editing via Music Synchronization Paper • 2603.29664 • Published 3 days ago • 40
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells Paper • 2603.25240 • Published 8 days ago • 73
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward Paper • 2603.26599 • Published 6 days ago • 48
LongCat-Next: Lexicalizing Modalities as Discrete Tokens Paper • 2603.27538 • Published 5 days ago • 125
view article Article Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents 3 days ago • 31
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Paper • 2603.24472 • Published 8 days ago • 47
RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models Paper • 2603.25502 • Published 8 days ago • 55
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens Paper • 2603.23516 • Published 28 days ago • 44