Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE Paper • 2610.27598 • Published 12 days ago • 41
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V Paper • 2610.28416 • Published 12 days ago • 42
SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published 13 days ago • 132 • 3
SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? Paper • 2610.26659 • Published 13 days ago • 132
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 276
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published Sep 17 • 215
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published Sep 25 • 82
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators Paper • 2607.20465 • Published May 19 • 57
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself Paper • 2609.22068 • Published Sep 18 • 133